{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"id":"85ELTcct_p1L"},"outputs":[],"source":["import warnings\n","warnings.filterwarnings('ignore')\n","import os\n","import pandas as pd\n","import numpy as np\n","import sklearn"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"dYapf89k_p1M"},"outputs":[],"source":["from sklearn.model_selection import train_test_split              # To split the data into train and test sets\n","from sklearn.metrics import accuracy_score, recall_score          # To compute error metrics\n","from sklearn.metrics import confusion_matrix\n","\n","from sklearn.tree import DecisionTreeClassifier                   # To build Decision tree model\n","from sklearn.ensemble import RandomForestClassifier               # To build Random forest model\n","\n","from sklearn.model_selection import GridSearchCV                  # To perform Grid Search using CV\n","import matplotlib.pyplot as plt\n","import seaborn as sns\n","%matplotlib inline\n","\n","from scipy import stats\n"]},{"cell_type":"markdown","metadata":{"id":"4-EEfo74_p1N"},"source":["### <font color = blue> Load the Data </font>"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"tmL4k9Tl_p1N"},"outputs":[],"source":["PATH = os.getcwd()\n","os.chdir(PATH)\n","data = pd.read_csv(\"Employee_Renege.csv\")"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"VA1ZnlUe_p1P","outputId":"64d6a125-e73d-411f-a973-38a77876b17b"},"outputs":[{"data":{"text/plain":["(1999, 17)"]},"execution_count":4,"metadata":{},"output_type":"execute_result"}],"source":["# Check the data dimensions\n","data.shape"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"OvN6LSvF_p1Q","outputId":"9c886a18-8e87-4f4b-dc1a-d4f81291bf9f"},"outputs":[{"data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>age</th>\n","      <th>marital_status</th>\n","      <th>education_level</th>\n","      <th>gender</th>\n","      <th>percent_hike</th>\n","      <th>distance_from_home</th>\n","      <th>sourcing_channel</th>\n","      <th>total_rounds</th>\n","      <th>date_1st_contact</th>\n","      <th>date_offered</th>\n","      <th>satisfaction_index</th>\n","      <th>no_companies_worked</th>\n","      <th>career_growth</th>\n","      <th>flexi_work</th>\n","      <th>total_experience</th>\n","      <th>timely_communication</th>\n","      <th>offer_dropped</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>29</td>\n","      <td>married</td>\n","      <td>Associate Certification</td>\n","      <td>Female</td>\n","      <td>27.0</td>\n","      <td>&lt;15 kms</td>\n","      <td>Internal Referrals</td>\n","      <td>8.0</td>\n","      <td>5/12/2015</td>\n","      <td>10/14/2015</td>\n","      <td>24</td>\n","      <td>3.0</td>\n","      <td>Lateral</td>\n","      <td>Yes</td>\n","      <td>5</td>\n","      <td>No</td>\n","      <td>Yes</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>37</td>\n","      <td>married</td>\n","      <td>Associate Degree</td>\n","      <td>Female</td>\n","      <td>22.0</td>\n","      <td>&lt;15 kms</td>\n","      <td>Consultants</td>\n","      <td>8.0</td>\n","      <td>3/9/2015</td>\n","      <td>9/3/2015</td>\n","      <td>20</td>\n","      <td>8.0</td>\n","      <td>Lateral</td>\n","      <td>Yes</td>\n","      <td>13</td>\n","      <td>No</td>\n","      <td>Yes</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>28</td>\n","      <td>married</td>\n","      <td>Associate Certification</td>\n","      <td>Female</td>\n","      <td>32.0</td>\n","      <td>&lt;15 kms</td>\n","      <td>Internal Referrals</td>\n","      <td>8.0</td>\n","      <td>12/17/2015</td>\n","      <td>5/22/2016</td>\n","      <td>23</td>\n","      <td>4.0</td>\n","      <td>Lateral</td>\n","      <td>Yes</td>\n","      <td>4</td>\n","      <td>No</td>\n","      <td>Yes</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>44</td>\n","      <td>married</td>\n","      <td>Associate Certification</td>\n","      <td>Female</td>\n","      <td>27.0</td>\n","      <td>&gt; 20 kms</td>\n","      <td>Job Portals</td>\n","      <td>9.0</td>\n","      <td>12/11/2015</td>\n","      <td>6/7/2016</td>\n","      <td>26</td>\n","      <td>6.0</td>\n","      <td>Lateral</td>\n","      <td>Yes</td>\n","      <td>20</td>\n","      <td>No</td>\n","      <td>Yes</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>32</td>\n","      <td>married</td>\n","      <td>Bachelor Degree</td>\n","      <td>Female</td>\n","      <td>28.0</td>\n","      <td>15-20 kms</td>\n","      <td>Company Website</td>\n","      <td>3.0</td>\n","      <td>2/13/2016</td>\n","      <td>3/11/2016</td>\n","      <td>53</td>\n","      <td>8.0</td>\n","      <td>Vertical</td>\n","      <td>Yes</td>\n","      <td>8</td>\n","      <td>No</td>\n","      <td>No</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["   age marital_status          education_level  gender  percent_hike  \\\n","0   29        married  Associate Certification  Female          27.0   \n","1   37        married         Associate Degree  Female          22.0   \n","2   28        married  Associate Certification  Female          32.0   \n","3   44        married  Associate Certification  Female          27.0   \n","4   32        married          Bachelor Degree  Female          28.0   \n","\n","  distance_from_home    sourcing_channel  total_rounds date_1st_contact  \\\n","0            <15 kms  Internal Referrals           8.0        5/12/2015   \n","1            <15 kms         Consultants           8.0         3/9/2015   \n","2            <15 kms  Internal Referrals           8.0       12/17/2015   \n","3           > 20 kms         Job Portals           9.0       12/11/2015   \n","4          15-20 kms     Company Website           3.0        2/13/2016   \n","\n","  date_offered  satisfaction_index  no_companies_worked career_growth  \\\n","0   10/14/2015                  24                  3.0       Lateral   \n","1     9/3/2015                  20                  8.0       Lateral   \n","2    5/22/2016                  23                  4.0       Lateral   \n","3     6/7/2016                  26                  6.0       Lateral   \n","4    3/11/2016                  53                  8.0      Vertical   \n","\n","  flexi_work  total_experience timely_communication offer_dropped  \n","0        Yes                 5                   No           Yes  \n","1        Yes                13                   No           Yes  \n","2        Yes                 4                   No           Yes  \n","3        Yes                20                   No           Yes  \n","4        Yes                 8                   No            No  "]},"execution_count":5,"metadata":{},"output_type":"execute_result"}],"source":["# Sample Data Check\n","data.head()"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"uOHb86oK_p1R","outputId":"d4c4fd7b-d4c1-4886-ec27-0b0f38dd345e"},"outputs":[{"data":{"text/plain":["age                       int64\n","marital_status           object\n","education_level          object\n","gender                   object\n","percent_hike            float64\n","distance_from_home       object\n","sourcing_channel         object\n","total_rounds            float64\n","date_1st_contact         object\n","date_offered             object\n","satisfaction_index        int64\n","no_companies_worked     float64\n","career_growth            object\n","flexi_work               object\n","total_experience          int64\n","timely_communication     object\n","offer_dropped            object\n","dtype: object"]},"execution_count":6,"metadata":{},"output_type":"execute_result"}],"source":["# Checking the Data Types\n","data.dtypes"]},{"cell_type":"markdown","metadata":{"id":"OCQMSevI_p1R"},"source":["Let us calculate the percentage of employees who dropped the offer. This will give an idea on how challenging is to hire an employee."]},{"cell_type":"code","execution_count":null,"metadata":{"id":"k-ITjCkf_p1S","outputId":"4ce5ae99-4066-4c8c-cb13-756a436e9398"},"outputs":[{"data":{"text/plain":["Yes    1024\n","No      975\n","Name: offer_dropped, dtype: int64"]},"execution_count":7,"metadata":{},"output_type":"execute_result"}],"source":["# Target Attribute \"offer_dropped\" frequency distribution\n","pd.value_counts(data[\"offer_dropped\"])"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"H4LG4EZI_p1S","outputId":"d229ac76-a1f4-449a-aba6-e6f40035061a"},"outputs":[{"name":"stdout","output_type":"stream","text":["0.512256128064032\n"]}],"source":["offer_dropped_percentage = len(data[data[\"offer_dropped\"] == \"Yes\"])/len(data[\"offer_dropped\"])\n","print(offer_dropped_percentage)"]},{"cell_type":"markdown","metadata":{"id":"6K0RoTFZ_p1T"},"source":["Lets have a look at data and see if there are any discrepancies like any attribute missing for employee and also observe the summary statistics."]},{"cell_type":"code","execution_count":null,"metadata":{"scrolled":true,"id":"gTZwzufC_p1T","outputId":"78d93291-91f5-4045-dae7-55fd66aecb0b"},"outputs":[{"data":{"text/plain":["age                     0\n","marital_status          0\n","education_level         0\n","gender                  0\n","percent_hike            1\n","distance_from_home      0\n","sourcing_channel        1\n","total_rounds            2\n","date_1st_contact        0\n","date_offered            0\n","satisfaction_index      0\n","no_companies_worked     2\n","career_growth           0\n","flexi_work              0\n","total_experience        0\n","timely_communication    0\n","offer_dropped           0\n","dtype: int64"]},"execution_count":9,"metadata":{},"output_type":"execute_result"}],"source":["# Missing Value Check\n","data.isnull().sum()"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"rbkUoStv_p1U","outputId":"022ee1ea-a1ef-4492-b793-cf9d32d147e7"},"outputs":[{"data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>age</th>\n","      <th>marital_status</th>\n","      <th>education_level</th>\n","      <th>gender</th>\n","      <th>percent_hike</th>\n","      <th>distance_from_home</th>\n","      <th>sourcing_channel</th>\n","      <th>total_rounds</th>\n","      <th>date_1st_contact</th>\n","      <th>date_offered</th>\n","      <th>satisfaction_index</th>\n","      <th>no_companies_worked</th>\n","      <th>career_growth</th>\n","      <th>flexi_work</th>\n","      <th>total_experience</th>\n","      <th>timely_communication</th>\n","      <th>offer_dropped</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>count</th>\n","      <td>1999.000000</td>\n","      <td>1999</td>\n","      <td>1999</td>\n","      <td>1999</td>\n","      <td>1998.000000</td>\n","      <td>1999</td>\n","      <td>1998</td>\n","      <td>1997.000000</td>\n","      <td>1999</td>\n","      <td>1999</td>\n","      <td>1999.000000</td>\n","      <td>1997.000000</td>\n","      <td>1999</td>\n","      <td>1999</td>\n","      <td>1999.000000</td>\n","      <td>1999</td>\n","      <td>1999</td>\n","    </tr>\n","    <tr>\n","      <th>unique</th>\n","      <td>NaN</td>\n","      <td>4</td>\n","      <td>4</td>\n","      <td>2</td>\n","      <td>NaN</td>\n","      <td>3</td>\n","      <td>5</td>\n","      <td>NaN</td>\n","      <td>252</td>\n","      <td>573</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>2</td>\n","      <td>2</td>\n","      <td>NaN</td>\n","      <td>2</td>\n","      <td>2</td>\n","    </tr>\n","    <tr>\n","      <th>top</th>\n","      <td>NaN</td>\n","      <td>married</td>\n","      <td>Associate Degree</td>\n","      <td>Male</td>\n","      <td>NaN</td>\n","      <td>&gt; 20 kms</td>\n","      <td>Job Portals</td>\n","      <td>NaN</td>\n","      <td>3/31/2015</td>\n","      <td>10/20/2015</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>Lateral</td>\n","      <td>Yes</td>\n","      <td>NaN</td>\n","      <td>No</td>\n","      <td>Yes</td>\n","    </tr>\n","    <tr>\n","      <th>freq</th>\n","      <td>NaN</td>\n","      <td>1389</td>\n","      <td>624</td>\n","      <td>1517</td>\n","      <td>NaN</td>\n","      <td>781</td>\n","      <td>486</td>\n","      <td>NaN</td>\n","      <td>54</td>\n","      <td>9</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>1286</td>\n","      <td>1177</td>\n","      <td>NaN</td>\n","      <td>1188</td>\n","      <td>1024</td>\n","    </tr>\n","    <tr>\n","      <th>mean</th>\n","      <td>35.378189</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>21.103604</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>6.485228</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>40.383692</td>\n","      <td>4.781673</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>11.103552</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>std</th>\n","      <td>6.132589</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>8.932102</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>2.605184</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>23.485313</td>\n","      <td>1.925830</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>6.057349</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>min</th>\n","      <td>25.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>10.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>3.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>15.000000</td>\n","      <td>1.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>1.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>25%</th>\n","      <td>30.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>13.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>4.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>22.000000</td>\n","      <td>3.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>6.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>50%</th>\n","      <td>35.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>19.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>7.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>29.000000</td>\n","      <td>5.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>11.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>75%</th>\n","      <td>41.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>29.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>9.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>59.000000</td>\n","      <td>6.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>16.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","    </tr>\n","    <tr>\n","      <th>max</th>\n","      <td>46.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>40.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>10.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>95.000000</td>\n","      <td>8.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>22.000000</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["                age marital_status   education_level gender  percent_hike  \\\n","count   1999.000000           1999              1999   1999   1998.000000   \n","unique          NaN              4                 4      2           NaN   \n","top             NaN        married  Associate Degree   Male           NaN   \n","freq            NaN           1389               624   1517           NaN   \n","mean      35.378189            NaN               NaN    NaN     21.103604   \n","std        6.132589            NaN               NaN    NaN      8.932102   \n","min       25.000000            NaN               NaN    NaN     10.000000   \n","25%       30.000000            NaN               NaN    NaN     13.000000   \n","50%       35.000000            NaN               NaN    NaN     19.000000   \n","75%       41.000000            NaN               NaN    NaN     29.000000   \n","max       46.000000            NaN               NaN    NaN     40.000000   \n","\n","       distance_from_home sourcing_channel  total_rounds date_1st_contact  \\\n","count                1999             1998   1997.000000             1999   \n","unique                  3                5           NaN              252   \n","top              > 20 kms      Job Portals           NaN        3/31/2015   \n","freq                  781              486           NaN               54   \n","mean                  NaN              NaN      6.485228              NaN   \n","std                   NaN              NaN      2.605184              NaN   \n","min                   NaN              NaN      3.000000              NaN   \n","25%                   NaN              NaN      4.000000              NaN   \n","50%                   NaN              NaN      7.000000              NaN   \n","75%                   NaN              NaN      9.000000              NaN   \n","max                   NaN              NaN     10.000000              NaN   \n","\n","       date_offered  satisfaction_index  no_companies_worked career_growth  \\\n","count          1999         1999.000000          1997.000000          1999   \n","unique          573                 NaN                  NaN             2   \n","top      10/20/2015                 NaN                  NaN       Lateral   \n","freq              9                 NaN                  NaN          1286   \n","mean            NaN           40.383692             4.781673           NaN   \n","std             NaN           23.485313             1.925830           NaN   \n","min             NaN           15.000000             1.000000           NaN   \n","25%             NaN           22.000000             3.000000           NaN   \n","50%             NaN           29.000000             5.000000           NaN   \n","75%             NaN           59.000000             6.000000           NaN   \n","max             NaN           95.000000             8.000000           NaN   \n","\n","       flexi_work  total_experience timely_communication offer_dropped  \n","count        1999       1999.000000                 1999          1999  \n","unique          2               NaN                    2             2  \n","top           Yes               NaN                   No           Yes  \n","freq         1177               NaN                 1188          1024  \n","mean          NaN         11.103552                  NaN           NaN  \n","std           NaN          6.057349                  NaN           NaN  \n","min           NaN          1.000000                  NaN           NaN  \n","25%           NaN          6.000000                  NaN           NaN  \n","50%           NaN         11.000000                  NaN           NaN  \n","75%           NaN         16.000000                  NaN           NaN  \n","max           NaN         22.000000                  NaN           NaN  "]},"execution_count":10,"metadata":{},"output_type":"execute_result"}],"source":["# Data Summary Understanding before data type conversions\n","data.describe(include = 'all')"]},{"cell_type":"markdown","metadata":{"id":"k65-h9BN_p1U"},"source":["## <font color = green> Data Preprocessing </font>"]},{"cell_type":"markdown","metadata":{"id":"qqyVpgk0_p1U"},"source":["### <font color = blue> Data Type Conversions </font>\n","\n","Before diving deep in to the data and understand the factors for __RENEGE__ and solve it lets do some data Pre-processing\n","When we read the data the date columns like date_offered, date_1st_contact and categorical columns like marital_status, education_level, gender etc... are read as Object in Pandas data frame.\n","Lets type cast them to appropriate types."]},{"cell_type":"code","execution_count":null,"metadata":{"id":"PpwcNgfk_p1V"},"outputs":[],"source":["# Convert variables to Date\n","cols = ['date_1st_contact','date_offered']\n","data[cols] = data[cols].apply(pd.to_datetime)\n"]},{"cell_type":"markdown","metadata":{"id":"95j5LMTh_p1V"},"source":["Checking data types after type casting"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"pYUj4Ho8_p1W","outputId":"03f0a65b-2f91-44c8-e98e-f7f71a70db00"},"outputs":[{"data":{"text/plain":["age                              int64\n","marital_status                  object\n","education_level                 object\n","gender                          object\n","percent_hike                   float64\n","distance_from_home              object\n","sourcing_channel                object\n","total_rounds                   float64\n","date_1st_contact        datetime64[ns]\n","date_offered            datetime64[ns]\n","satisfaction_index               int64\n","no_companies_worked            float64\n","career_growth                   object\n","flexi_work                      object\n","total_experience                 int64\n","timely_communication            object\n","offer_dropped                   object\n","dtype: object"]},"execution_count":12,"metadata":{},"output_type":"execute_result"}],"source":["data.dtypes"]},{"cell_type":"markdown","metadata":{"id":"9IypNzNN_p1W"},"source":["#### <font color = brown>Convert all category variables and check</font>"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"4mQP1y5w_p1W"},"outputs":[],"source":["# Convert variables to Category\n","cat_cols = data.select_dtypes(include=['object']).columns\n","for col in cat_cols:\n","    data[col] = data[col].astype(\"category\")"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"3Mltvap5_p1X","outputId":"c5099c34-1d90-4b73-80bd-9ce25ce1d4a3"},"outputs":[{"data":{"text/plain":["age                              int64\n","marital_status                category\n","education_level               category\n","gender                        category\n","percent_hike                   float64\n","distance_from_home            category\n","sourcing_channel              category\n","total_rounds                   float64\n","date_1st_contact        datetime64[ns]\n","date_offered            datetime64[ns]\n","satisfaction_index               int64\n","no_companies_worked            float64\n","career_growth                 category\n","flexi_work                    category\n","total_experience                 int64\n","timely_communication          category\n","offer_dropped                 category\n","dtype: object"]},"execution_count":14,"metadata":{},"output_type":"execute_result"}],"source":["data.dtypes"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"A1iZIqg4_p1Y"},"outputs":[],"source":["data1 = data.dropna(axis = 0)"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"eWO6ArvI_p1Y","outputId":"c36a41da-e092-4bde-e849-62c5b2393356"},"outputs":[{"data":{"text/plain":["(1993, 17)"]},"execution_count":16,"metadata":{},"output_type":"execute_result"}],"source":["data1.shape"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"_oJLuBP9_p1Z","outputId":"b00b137a-7849-4527-ff65-6d1493c722bd"},"outputs":[{"name":"stdout","output_type":"stream","text":["(1999, 17)\n"]}],"source":["print(data.shape)\n"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"njrDh0q9_p1Z","outputId":"843aa532-22ca-486a-f944-f87130c2f506"},"outputs":[{"data":{"text/plain":["age                     0\n","marital_status          0\n","education_level         0\n","gender                  0\n","percent_hike            1\n","distance_from_home      0\n","sourcing_channel        1\n","total_rounds            2\n","date_1st_contact        0\n","date_offered            0\n","satisfaction_index      0\n","no_companies_worked     2\n","career_growth           0\n","flexi_work              0\n","total_experience        0\n","timely_communication    0\n","offer_dropped           0\n","dtype: int64"]},"execution_count":19,"metadata":{},"output_type":"execute_result"}],"source":["data.isnull().sum()"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"8i9SIlxs_p1b","outputId":"cf6ab790-c693-4ed4-e3fc-b35b04711d24"},"outputs":[{"name":"stdout","output_type":"stream","text":["Index(['age', 'percent_hike', 'total_rounds', 'satisfaction_index',\n","       'no_companies_worked', 'total_experience'],\n","      dtype='object')\n"]},{"data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>marital_status</th>\n","      <th>education_level</th>\n","      <th>gender</th>\n","      <th>distance_from_home</th>\n","      <th>sourcing_channel</th>\n","      <th>career_growth</th>\n","      <th>flexi_work</th>\n","      <th>timely_communication</th>\n","      <th>offer_dropped</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>married</td>\n","      <td>Associate Certification</td>\n","      <td>Female</td>\n","      <td>&lt;15 kms</td>\n","      <td>Internal Referrals</td>\n","      <td>Lateral</td>\n","      <td>Yes</td>\n","      <td>No</td>\n","      <td>Yes</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>married</td>\n","      <td>Associate Degree</td>\n","      <td>Female</td>\n","      <td>&lt;15 kms</td>\n","      <td>Consultants</td>\n","      <td>Lateral</td>\n","      <td>Yes</td>\n","      <td>No</td>\n","      <td>Yes</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>married</td>\n","      <td>Associate Certification</td>\n","      <td>Female</td>\n","      <td>&lt;15 kms</td>\n","      <td>Internal Referrals</td>\n","      <td>Lateral</td>\n","      <td>Yes</td>\n","      <td>No</td>\n","      <td>Yes</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>married</td>\n","      <td>Associate Certification</td>\n","      <td>Female</td>\n","      <td>&gt; 20 kms</td>\n","      <td>Job Portals</td>\n","      <td>Lateral</td>\n","      <td>Yes</td>\n","      <td>No</td>\n","      <td>Yes</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>married</td>\n","      <td>Bachelor Degree</td>\n","      <td>Female</td>\n","      <td>15-20 kms</td>\n","      <td>Company Website</td>\n","      <td>Vertical</td>\n","      <td>Yes</td>\n","      <td>No</td>\n","      <td>No</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["  marital_status          education_level  gender distance_from_home  \\\n","0        married  Associate Certification  Female            <15 kms   \n","1        married         Associate Degree  Female            <15 kms   \n","2        married  Associate Certification  Female            <15 kms   \n","3        married  Associate Certification  Female           > 20 kms   \n","4        married          Bachelor Degree  Female          15-20 kms   \n","\n","     sourcing_channel career_growth flexi_work timely_communication  \\\n","0  Internal Referrals       Lateral        Yes                   No   \n","1         Consultants       Lateral        Yes                   No   \n","2  Internal Referrals       Lateral        Yes                   No   \n","3         Job Portals       Lateral        Yes                   No   \n","4     Company Website      Vertical        Yes                   No   \n","\n","  offer_dropped  \n","0           Yes  \n","1           Yes  \n","2           Yes  \n","3           Yes  \n","4            No  "]},"execution_count":20,"metadata":{},"output_type":"execute_result"}],"source":["num_cols = data.select_dtypes(include=['float64','int64'])\n","cat_cols = data.select_dtypes(include=['category'])\n","print(num_cols.columns) # print the numeric columns\n","cat_cols.head()"]},{"cell_type":"markdown","metadata":{"id":"EG8h58zP_p1b"},"source":["Missing values imputation\n"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"7VQILOln_p1c","outputId":"683a591f-02b4-4d7f-a928-055646b61fde"},"outputs":[{"data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>marital_status</th>\n","      <th>education_level</th>\n","      <th>gender</th>\n","      <th>distance_from_home</th>\n","      <th>sourcing_channel</th>\n","      <th>career_growth</th>\n","      <th>flexi_work</th>\n","      <th>timely_communication</th>\n","      <th>offer_dropped</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>married</td>\n","      <td>Associate Certification</td>\n","      <td>Female</td>\n","      <td>&lt;15 kms</td>\n","      <td>Internal Referrals</td>\n","      <td>Lateral</td>\n","      <td>Yes</td>\n","      <td>No</td>\n","      <td>Yes</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>married</td>\n","      <td>Associate Degree</td>\n","      <td>Female</td>\n","      <td>&lt;15 kms</td>\n","      <td>Consultants</td>\n","      <td>Lateral</td>\n","      <td>Yes</td>\n","      <td>No</td>\n","      <td>Yes</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>married</td>\n","      <td>Associate Certification</td>\n","      <td>Female</td>\n","      <td>&lt;15 kms</td>\n","      <td>Internal Referrals</td>\n","      <td>Lateral</td>\n","      <td>Yes</td>\n","      <td>No</td>\n","      <td>Yes</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>married</td>\n","      <td>Associate Certification</td>\n","      <td>Female</td>\n","      <td>&gt; 20 kms</td>\n","      <td>Job Portals</td>\n","      <td>Lateral</td>\n","      <td>Yes</td>\n","      <td>No</td>\n","      <td>Yes</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>married</td>\n","      <td>Bachelor Degree</td>\n","      <td>Female</td>\n","      <td>15-20 kms</td>\n","      <td>Company Website</td>\n","      <td>Vertical</td>\n","      <td>Yes</td>\n","      <td>No</td>\n","      <td>No</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["  marital_status          education_level  gender distance_from_home  \\\n","0        married  Associate Certification  Female            <15 kms   \n","1        married         Associate Degree  Female            <15 kms   \n","2        married  Associate Certification  Female            <15 kms   \n","3        married  Associate Certification  Female           > 20 kms   \n","4        married          Bachelor Degree  Female          15-20 kms   \n","\n","     sourcing_channel career_growth flexi_work timely_communication  \\\n","0  Internal Referrals       Lateral        Yes                   No   \n","1         Consultants       Lateral        Yes                   No   \n","2  Internal Referrals       Lateral        Yes                   No   \n","3         Job Portals       Lateral        Yes                   No   \n","4     Company Website      Vertical        Yes                   No   \n","\n","  offer_dropped  \n","0           Yes  \n","1           Yes  \n","2           Yes  \n","3           Yes  \n","4            No  "]},"execution_count":21,"metadata":{},"output_type":"execute_result"}],"source":["from sklearn.impute import SimpleImputer\n","imp = SimpleImputer(missing_values=np.nan,strategy='mean')\n","num_data = pd.DataFrame(imp.fit_transform(num_cols),columns=num_cols.columns)\n","imp = SimpleImputer(missing_values=np.nan,strategy='most_frequent')\n","cat_data = pd.DataFrame(imp.fit_transform(cat_cols),columns=cat_cols.columns)\n","cat_data.head()"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"MvvGCFiV_p1c","outputId":"8cf841ca-1858-4b6a-ced0-67a3053215ae"},"outputs":[{"data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>age</th>\n","      <th>percent_hike</th>\n","      <th>total_rounds</th>\n","      <th>satisfaction_index</th>\n","      <th>no_companies_worked</th>\n","      <th>total_experience</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>29.0</td>\n","      <td>27.0</td>\n","      <td>8.0</td>\n","      <td>24.0</td>\n","      <td>3.0</td>\n","      <td>5.0</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>37.0</td>\n","      <td>22.0</td>\n","      <td>8.0</td>\n","      <td>20.0</td>\n","      <td>8.0</td>\n","      <td>13.0</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>28.0</td>\n","      <td>32.0</td>\n","      <td>8.0</td>\n","      <td>23.0</td>\n","      <td>4.0</td>\n","      <td>4.0</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>44.0</td>\n","      <td>27.0</td>\n","      <td>9.0</td>\n","      <td>26.0</td>\n","      <td>6.0</td>\n","      <td>20.0</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>32.0</td>\n","      <td>28.0</td>\n","      <td>3.0</td>\n","      <td>53.0</td>\n","      <td>8.0</td>\n","      <td>8.0</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["    age  percent_hike  total_rounds  satisfaction_index  no_companies_worked  \\\n","0  29.0          27.0           8.0                24.0                  3.0   \n","1  37.0          22.0           8.0                20.0                  8.0   \n","2  28.0          32.0           8.0                23.0                  4.0   \n","3  44.0          27.0           9.0                26.0                  6.0   \n","4  32.0          28.0           3.0                53.0                  8.0   \n","\n","   total_experience  \n","0               5.0  \n","1              13.0  \n","2               4.0  \n","3              20.0  \n","4               8.0  "]},"execution_count":22,"metadata":{},"output_type":"execute_result"}],"source":["num_data.head()"]},{"cell_type":"markdown","metadata":{"id":"580CE1qS_p1d"},"source":["Getting the Final dataset after conversions and missing values imputation"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"xDCH7D9Y_p1d","outputId":"f723f336-a8c7-481a-8d42-eac9b9c7bb27"},"outputs":[{"data":{"text/plain":["Index(['age', 'marital_status', 'education_level', 'gender', 'percent_hike',\n","       'distance_from_home', 'sourcing_channel', 'total_rounds',\n","       'date_1st_contact', 'date_offered', 'satisfaction_index',\n","       'no_companies_worked', 'career_growth', 'flexi_work',\n","       'total_experience', 'timely_communication', 'offer_dropped'],\n","      dtype='object')"]},"execution_count":23,"metadata":{},"output_type":"execute_result"}],"source":["data.columns"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"n0PnH78Z_p1e","outputId":"4ed84c8c-ef58-4d28-9325-0575bb4615f9"},"outputs":[{"data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>age</th>\n","      <th>percent_hike</th>\n","      <th>total_rounds</th>\n","      <th>satisfaction_index</th>\n","      <th>no_companies_worked</th>\n","      <th>total_experience</th>\n","      <th>marital_status</th>\n","      <th>education_level</th>\n","      <th>gender</th>\n","      <th>distance_from_home</th>\n","      <th>sourcing_channel</th>\n","      <th>career_growth</th>\n","      <th>flexi_work</th>\n","      <th>timely_communication</th>\n","      <th>offer_dropped</th>\n","      <th>date_1st_contact</th>\n","      <th>date_offered</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>29.0</td>\n","      <td>27.0</td>\n","      <td>8.0</td>\n","      <td>24.0</td>\n","      <td>3.0</td>\n","      <td>5.0</td>\n","      <td>married</td>\n","      <td>Associate Certification</td>\n","      <td>Female</td>\n","      <td>&lt;15 kms</td>\n","      <td>Internal Referrals</td>\n","      <td>Lateral</td>\n","      <td>Yes</td>\n","      <td>No</td>\n","      <td>Yes</td>\n","      <td>2015-05-12</td>\n","      <td>2015-10-14</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>37.0</td>\n","      <td>22.0</td>\n","      <td>8.0</td>\n","      <td>20.0</td>\n","      <td>8.0</td>\n","      <td>13.0</td>\n","      <td>married</td>\n","      <td>Associate Degree</td>\n","      <td>Female</td>\n","      <td>&lt;15 kms</td>\n","      <td>Consultants</td>\n","      <td>Lateral</td>\n","      <td>Yes</td>\n","      <td>No</td>\n","      <td>Yes</td>\n","      <td>2015-03-09</td>\n","      <td>2015-09-03</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>28.0</td>\n","      <td>32.0</td>\n","      <td>8.0</td>\n","      <td>23.0</td>\n","      <td>4.0</td>\n","      <td>4.0</td>\n","      <td>married</td>\n","      <td>Associate Certification</td>\n","      <td>Female</td>\n","      <td>&lt;15 kms</td>\n","      <td>Internal Referrals</td>\n","      <td>Lateral</td>\n","      <td>Yes</td>\n","      <td>No</td>\n","      <td>Yes</td>\n","      <td>2015-12-17</td>\n","      <td>2016-05-22</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>44.0</td>\n","      <td>27.0</td>\n","      <td>9.0</td>\n","      <td>26.0</td>\n","      <td>6.0</td>\n","      <td>20.0</td>\n","      <td>married</td>\n","      <td>Associate Certification</td>\n","      <td>Female</td>\n","      <td>&gt; 20 kms</td>\n","      <td>Job Portals</td>\n","      <td>Lateral</td>\n","      <td>Yes</td>\n","      <td>No</td>\n","      <td>Yes</td>\n","      <td>2015-12-11</td>\n","      <td>2016-06-07</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>32.0</td>\n","      <td>28.0</td>\n","      <td>3.0</td>\n","      <td>53.0</td>\n","      <td>8.0</td>\n","      <td>8.0</td>\n","      <td>married</td>\n","      <td>Bachelor Degree</td>\n","      <td>Female</td>\n","      <td>15-20 kms</td>\n","      <td>Company Website</td>\n","      <td>Vertical</td>\n","      <td>Yes</td>\n","      <td>No</td>\n","      <td>No</td>\n","      <td>2016-02-13</td>\n","      <td>2016-03-11</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["    age  percent_hike  total_rounds  satisfaction_index  no_companies_worked  \\\n","0  29.0          27.0           8.0                24.0                  3.0   \n","1  37.0          22.0           8.0                20.0                  8.0   \n","2  28.0          32.0           8.0                23.0                  4.0   \n","3  44.0          27.0           9.0                26.0                  6.0   \n","4  32.0          28.0           3.0                53.0                  8.0   \n","\n","   total_experience marital_status          education_level  gender  \\\n","0               5.0        married  Associate Certification  Female   \n","1              13.0        married         Associate Degree  Female   \n","2               4.0        married  Associate Certification  Female   \n","3              20.0        married  Associate Certification  Female   \n","4               8.0        married          Bachelor Degree  Female   \n","\n","  distance_from_home    sourcing_channel career_growth flexi_work  \\\n","0            <15 kms  Internal Referrals       Lateral        Yes   \n","1            <15 kms         Consultants       Lateral        Yes   \n","2            <15 kms  Internal Referrals       Lateral        Yes   \n","3           > 20 kms         Job Portals       Lateral        Yes   \n","4          15-20 kms     Company Website      Vertical        Yes   \n","\n","  timely_communication offer_dropped date_1st_contact date_offered  \n","0                   No           Yes       2015-05-12   2015-10-14  \n","1                   No           Yes       2015-03-09   2015-09-03  \n","2                   No           Yes       2015-12-17   2016-05-22  \n","3                   No           Yes       2015-12-11   2016-06-07  \n","4                   No            No       2016-02-13   2016-03-11  "]},"execution_count":24,"metadata":{},"output_type":"execute_result"}],"source":["data_final = pd.concat([num_data,cat_data,data.loc[:,[\"date_1st_contact\",\"date_offered\"]]],axis=1)\n","data_final.head(5)"]},{"cell_type":"markdown","metadata":{"id":"MlncGQMJ_p1f"},"source":["### <font color = blue>Feature Engineering - New Variable Creation </font>"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"1pnOD_JZ_p1g"},"outputs":[],"source":["# Create job hopping index: jhi\n","\n","data_final[\"jhi\"] = data_final[\"total_experience\"]/data_final[\"no_companies_worked\"]"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"d64gxS6A_p1g"},"outputs":[],"source":["# create days to offer: days_offered\n","\n","data_final[\"days_offered\"] = pd.to_datetime(data_final[\"date_offered\"],format='%m/%d/%Y') - pd.to_datetime(data_final[\"date_1st_contact\"],format='%m/%d/%Y')\n","\n"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"UODsyOGz_p1h","outputId":"7c3b69d4-ddc0-400b-9717-f733aa3a1477"},"outputs":[{"data":{"text/plain":["0   155 days\n","1   178 days\n","2   157 days\n","3   179 days\n","4    27 days\n","Name: days_offered, dtype: timedelta64[ns]"]},"execution_count":28,"metadata":{},"output_type":"execute_result"}],"source":["data_final[\"days_offered\"].head()"]},{"cell_type":"markdown","metadata":{"id":"G-OHt_ed_p1h"},"source":["Days offered column data type is given as time delta. we need to convert it to integer"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"iii48NBx_p1i"},"outputs":[],"source":["data_final[\"days_offered\"] = np.int64(data_final[\"days_offered\"]/np.timedelta64(1,'D'))"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"-mVgmMKR_p1i","outputId":"4e7d377a-915f-42d7-c381-f623e6f9ea8a"},"outputs":[{"data":{"text/plain":["0    155\n","1    178\n","2    157\n","3    179\n","4     27\n","Name: days_offered, dtype: int64"]},"execution_count":30,"metadata":{},"output_type":"execute_result"}],"source":["data_final[\"days_offered\"].head()"]},{"cell_type":"markdown","metadata":{"id":"dMQsoiJh_p1j"},"source":["Before further Analysis lets drop all the unnecessary attributes from the data set. This will help in reducing the computational over head and time with huge data sets. This is very important part of engineering"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"I0EYxEXQ_p1j","outputId":"21ef1f07-0ded-4df5-ce9e-539cfbe4a3af"},"outputs":[{"data":{"text/plain":["(1999, 17)"]},"execution_count":31,"metadata":{},"output_type":"execute_result"}],"source":["data.shape"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"dY2drM-g_p1j"},"outputs":[],"source":["# Remove original variables for avoiding redundancy : \"date_1st_contact\", \"date_offered\", \"no_companies_worked\", \"total_experience\"\n","# Remove variables you think are not possible to collect : \"satisfaction_index\"\n","data_final=data_final.loc[:,data_final.columns.difference([\"date_1st_contact\",\"date_offered\",\"no_companies_worked\",\"total_experience\",\"satisfaction_index\"])]\n","\n","\n"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"kmnq6LuY_p1k","outputId":"74b4cfb0-6ed5-4d7e-ab83-a3533a3014a2"},"outputs":[{"data":{"text/plain":["(1999, 14)"]},"execution_count":33,"metadata":{},"output_type":"execute_result"}],"source":["\n","data_final.shape"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"HKFc67sY_p1k"},"outputs":[],"source":["data = data_final.copy()"]},{"cell_type":"markdown","metadata":{"id":"Jm_18z5V_p1k"},"source":["## <font color = green>Exploratory Data Analysis</font>"]},{"cell_type":"markdown","metadata":{"id":"id0D98Gt_p1l"},"source":["### <font color = blue>Univariate Analysis</font>\n","\n","Univariate analysis is perhaps the simplest form of statistical analysis. Like other forms of statistics, it can be inferential or descriptive. The key fact is that only one variable is involved.\n","\n","We will start with categorical variables"]},{"cell_type":"markdown","metadata":{"id":"1xbHlmpI_p1m"},"source":["#### <font color = brown> Marital Status - Visual approach </font>"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"4tZPhC6K_p1m","outputId":"daa9a669-a16e-46be-ab15-1b8a1b9b1288"},"outputs":[{"data":{"image/png":"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\n","text/plain":["<Figure size 720x360 with 1 Axes>"]},"metadata":{},"output_type":"display_data"}],"source":["plt.figure(figsize = (10,5)) # Setting figure parameters\n","sns.set(style=\"darkgrid\")\n","sns.countplot(x='marital_status', data=data).set_title('marital_status') # Plot\n","plt.xticks(rotation = 75) # Setting labels\n","plt.show()"]},{"cell_type":"markdown","metadata":{"id":"DxyQRfFi_p1m"},"source":["__Insight: The bar chart shows married candidates have highest frequency__"]},{"cell_type":"markdown","metadata":{"id":"PYTnpyoJ_p1n"},"source":["#### <font color = brown> Martial Status - Metric approach </font>"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"U4_ohBU7_p1n","outputId":"dd5d9607-2949-4f4c-8fec-c0cd121c80fa"},"outputs":[{"name":"stdout","output_type":"stream","text":["0.6948474237118559\n"]}],"source":["martial_status_perc = len(data[data['marital_status'] == \"married\"])/len(data['marital_status'])\n","print(martial_status_perc)\n"]},{"cell_type":"markdown","metadata":{"id":"WMHgb2zZ_p1n"},"source":["__Insight: Married candidates have 69% of the total__"]},{"cell_type":"markdown","metadata":{"id":"LTHVjA3b_p1o"},"source":["#### <font color =brown> Age Distribution - Visual approach </font>"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"GjhNs4ha_p1o","outputId":"3bb95ff0-0c68-4513-ab43-5b6fb81bd59a"},"outputs":[{"data":{"image/png":"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\n","text/plain":["<Figure size 576x288 with 1 Axes>"]},"metadata":{},"output_type":"display_data"}],"source":["plt.figure(figsize = (8,4))\n","b = sns.distplot(data['age'],kde=False,bins = 5)\n","b.set_title('Histogram of Age',fontsize = 16)\n","b.set_xlabel(\"Age\",fontsize=14)\n","plt.show()"]},{"cell_type":"markdown","metadata":{"id":"q94EK4C3_p1o"},"source":["__Insight: There is no significance change in the age groups__"]},{"cell_type":"markdown","metadata":{"id":"4H4-WY7r_p1p"},"source":["#### <font color = brown>Job Hopping Index - Visual approach</font>"]},{"cell_type":"code","execution_count":null,"metadata":{"scrolled":true,"id":"bwxbWo5n_p1p","outputId":"42079ad6-2779-4660-fbe5-eed9fdfa4a8f"},"outputs":[{"data":{"image/png":"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\n","text/plain":["<Figure size 576x288 with 1 Axes>"]},"metadata":{},"output_type":"display_data"}],"source":["plt.figure(figsize = (8,4))\n","b = sns.distplot(data['jhi'],kde=False,bins=6)\n","b.set_title('Histogram of job hopping index',fontsize = 16)\n","b.set_xlabel(\"job hopping index\",fontsize=14)\n","plt.show()"]},{"cell_type":"markdown","metadata":{"id":"tDP6zr5V_p1q"},"source":["__Insight: Maximum job hopping index ranges from 0.5 to 3__"]},{"cell_type":"markdown","metadata":{"id":"5lh8E7zy_p1q"},"source":["#### <font color = brown>Job Hopping Index - Metric approach </font>"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"e5rkX7Eu_p1q","outputId":"4fe03cb5-e719-457e-ba88-413924899549"},"outputs":[{"data":{"text/plain":["count    1999.000000\n","mean        2.367537\n","std         1.272728\n","min         0.500000\n","25%         1.400000\n","50%         2.142857\n","75%         3.000000\n","max         7.333333\n","Name: jhi, dtype: float64"]},"execution_count":47,"metadata":{},"output_type":"execute_result"}],"source":["data[\"jhi\"].describe()"]},{"cell_type":"markdown","metadata":{"id":"_ok3l09W_p1r"},"source":["__Insight: Higher job hoping index at 7.5 and lower at 0.5__"]},{"cell_type":"markdown","metadata":{"id":"VC0wsH53_p1s"},"source":["#### <font color = brown> Days Offered - Visual approach</font>"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"aKzJNakB_p1s","outputId":"15647066-c2e1-43d8-8628-f8b0a0e666ef"},"outputs":[{"data":{"text/plain":["Index(['age', 'career_growth', 'days_offered', 'distance_from_home',\n","       'education_level', 'flexi_work', 'gender', 'jhi', 'marital_status',\n","       'offer_dropped', 'percent_hike', 'sourcing_channel',\n","       'timely_communication', 'total_rounds'],\n","      dtype='object')"]},"execution_count":48,"metadata":{},"output_type":"execute_result"}],"source":["data_final.columns"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"EABHJxQ4_p1t","outputId":"5d173add-bf69-40a6-d42f-e159d9e9c1b1"},"outputs":[{"data":{"image/png":"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\n","text/plain":["<Figure size 576x288 with 1 Axes>"]},"metadata":{},"output_type":"display_data"}],"source":["plt.figure(figsize = (8,4))\n","b = sns.distplot(data['days_offered'],kde = False)\n","b.set_title('days_offered',fontsize = 16)\n","b.set_xlabel(\"days_offered\",fontsize=14)\n","plt.show()"]},{"cell_type":"markdown","metadata":{"id":"gK-iLapB_p1u"},"source":["__Insight: Candidates were offered job as less as 1 day to maximum 180 days__"]},{"cell_type":"markdown","metadata":{"id":"P7X7uPPg_p1u"},"source":["#### <font color = brown> Days Offered - Metric approach</font>"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"yH5f9xQ__p1v","outputId":"5bfd06a9-9c31-4561-81b7-979ff5dcd1ff"},"outputs":[{"name":"stdout","output_type":"stream","text":["0.29164582291145574\n"]}],"source":["days_offered_gt_120 = len(data[data['days_offered'] > 120])/len(data['days_offered'])\n","print(days_offered_gt_120)"]},{"cell_type":"markdown","metadata":{"id":"bsnvY_HG_p1w"},"source":["__Insight: Approx 30% of candidates were offered job after 120 days__"]},{"cell_type":"markdown","metadata":{"id":"t6_JkJHK_p1w"},"source":["<font color = red> Activity for practice </font>"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"PLPP0fhY_p1x","outputId":"a14b880e-8b3c-49eb-c25d-4a62bcb32980"},"outputs":[{"data":{"text/plain":["Index(['age', 'career_growth', 'days_offered', 'distance_from_home',\n","       'education_level', 'flexi_work', 'gender', 'jhi', 'marital_status',\n","       'offer_dropped', 'percent_hike', 'sourcing_channel',\n","       'timely_communication', 'total_rounds'],\n","      dtype='object')"]},"execution_count":51,"metadata":{},"output_type":"execute_result"}],"source":["\n","## Analyse the distribution and patterns for the remaining variables\n","data.columns"]},{"cell_type":"markdown","metadata":{"id":"a487S4ei_p1x"},"source":["### <font color = blue>Bivariate Analysis</font>\n","\n","Bivariate Analysis is done between two variables. Nature of variables can be Categorical or Numerical;\n","Different charts and statistics are used to understand the relationship between two variables such as:\n","1. Numerical vs Numerical Variable\n","   Visualisations : Correlation Plot, Scatter Plot, Line Chart, regression chart\n","   Statistical Approach: correlation or covariance values, ANOVA method, Regression Analysis\n","2. Categorical vs Categorical Variable\n","   Visualisations : Bar Plot, Stacked Bar Chart, Grouped Bar Chart, Advanced Charts\n","   Statistical Approach : Prop Table Analysis, Chi-Square Test of Independence\n","3. Numerical vs Categorical Variable:\n","   Visualisations : Box Plot with Categorical variable on x-axis, Advanced Charts\n","   Statistical Approach : Two Sample T-Test\n","   \n","Bivariate Analysis can be done between any two independent variables;\n","However, analysis of independent variable w.r.t dependent variable (target) is very important\n","     "]},{"cell_type":"code","execution_count":null,"metadata":{"id":"03SJKfID_p1y","outputId":"265a45cd-a2ad-436e-b3e9-a9d808835d8c"},"outputs":[{"data":{"text/plain":["age                      float64\n","career_growth           category\n","days_offered               int64\n","distance_from_home      category\n","flexi_work              category\n","jhi                      float64\n","offer_dropped           category\n","percent_hike             float64\n","sourcing_channel        category\n","timely_communication    category\n","total_rounds             float64\n","dtype: object"]},"execution_count":129,"metadata":{},"output_type":"execute_result"}],"source":["data.dtypes"]},{"cell_type":"markdown","metadata":{"id":"bmeL-KZh_p1z"},"source":["#### <font color = brown>Numeric to Numeric Variables Relationship Analysis</font>\n","\n","Let us examine if any 2 pieces of data for an employee have a relation. There are 17 attributes how to know if there is a relation between 2 variables. The best way to know about this is by calculating the correlation between all the pairs of numerical data.<br>\n","This is called __CORRELATION ANALYSIS__\n","<br><br>\n","The best way to do the correlation analysis is by plotting them."]},{"cell_type":"code","execution_count":null,"metadata":{"id":"PJHPeqxE_p1z","outputId":"ca93ff35-8290-4515-d048-99633722ada4"},"outputs":[{"data":{"text/plain":["<matplotlib.axes._subplots.AxesSubplot at 0x120790ba8>"]},"execution_count":53,"metadata":{},"output_type":"execute_result"},{"data":{"image/png":"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\n","text/plain":["<Figure size 432x432 with 2 Axes>"]},"metadata":{},"output_type":"display_data"}],"source":["f, ax = plt.subplots(figsize=(6, 6))\n","corr = data.corr(method='pearson')\n","sns.heatmap(corr,square=True, ax=ax,annot=True,fmt=\".1f\")\n"]},{"cell_type":"markdown","metadata":{"id":"7mL_HaYV_p10"},"source":["__(days_offered,percent_hike), (age,jhi) are correlated above 0.60__"]},{"cell_type":"markdown","metadata":{"id":"-q0BpVJn_p11"},"source":["It is good idea to see the relation between the following attributes\n","- days_offered vs sourcing_channel\n","- education level vs job hopping index\n","\n","<br>\n","If you observe in the above 2 cases one variable is numerical variable and the other one is categorical variable.\n","\n","So this is __Numerical variable relationship w.r.t Category__\n","<br> Let us see how to plot them."]},{"cell_type":"markdown","metadata":{"id":"oBGGwaVZ_p11"},"source":["#### <font color = brown>days_offered vs sourcing_channel</font>"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"vcbBIhM2_p12","outputId":"91087881-db7d-4393-d0e8-f0944db4af81"},"outputs":[{"data":{"image/png":"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\n","text/plain":["<Figure size 576x288 with 1 Axes>"]},"metadata":{},"output_type":"display_data"}],"source":["plt.figure(figsize = (8,4))\n","\n","g = sns.boxplot(x=\"sourcing_channel\",y=\"days_offered\", data=data)\n","\n","plt.title('sourcing_channel and days_offered',fontsize = 16)\n","plt.ylim ([0,200])\n","\n","plt.ylabel(\"days_offered\",fontsize=12)\n","plt.xlabel(\"sourcing_channel\",fontsize=12)\n","plt.show()"]},{"cell_type":"markdown","metadata":{"id":"LWw6mwHo_p12"},"source":["#### <font color=brown>education level vs job hopping index</font>"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"X_TPbjX4_p13","outputId":"0398a0c9-d3dc-4915-c813-93e79b554f05"},"outputs":[{"data":{"text/plain":["Index(['age', 'career_growth', 'days_offered', 'distance_from_home',\n","       'education_level', 'flexi_work', 'gender', 'jhi', 'marital_status',\n","       'offer_dropped', 'percent_hike', 'sourcing_channel',\n","       'timely_communication', 'total_rounds'],\n","      dtype='object')"]},"execution_count":55,"metadata":{},"output_type":"execute_result"}],"source":["data.columns"]},{"cell_type":"code","execution_count":null,"metadata":{"scrolled":true,"id":"IuwPNShk_p13","outputId":"b91e4f7f-4a82-4711-8351-4e36111fa232"},"outputs":[{"data":{"image/png":"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\n","text/plain":["<Figure size 576x288 with 1 Axes>"]},"metadata":{},"output_type":"display_data"}],"source":["plt.figure(figsize = (8,4))\n","\n","g = sns.boxplot(x=\"education_level\",y=\"jhi\", data=data_final)\n","\n","plt.title('education_level and jhi',fontsize = 16)\n","plt.ylim ([0,10])\n","\n","plt.ylabel(\"jhi\",fontsize=12)\n","plt.xlabel(\"education_level\",fontsize=12)\n","plt.show()"]},{"cell_type":"markdown","metadata":{"id":"ZsbejivP_p14"},"source":["### <font color = blue>Exploratory Data Analysis w.r.t Target Variable \"offer_dropped\"</font>\n","\n","Here we are trying to understand why employees are dropping the offer. So the target variable is offer_dropped.\n","It is good thing to understand the relationship between different variables versus the target variable."]},{"cell_type":"markdown","metadata":{"id":"7ofeqi3M_p14"},"source":["#### <font color= brown>Category vs Category Variable Analysis</font>\n","#### <font color = brown>sourcing_channel vs offer_dropped</font>"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"pwx1eHjy_p15","outputId":"e6701807-f8d1-4fc6-c06c-ba947b77b2e8"},"outputs":[{"data":{"text/html":["<div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th>offer_dropped</th>\n","      <th>No</th>\n","      <th>Yes</th>\n","    </tr>\n","    <tr>\n","      <th>sourcing_channel</th>\n","      <th></th>\n","      <th></th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>Company Website</th>\n","      <td>204</td>\n","      <td>149</td>\n","    </tr>\n","    <tr>\n","      <th>Consultants</th>\n","      <td>194</td>\n","      <td>264</td>\n","    </tr>\n","    <tr>\n","      <th>Internal Referrals</th>\n","      <td>85</td>\n","      <td>196</td>\n","    </tr>\n","    <tr>\n","      <th>Job Portals</th>\n","      <td>284</td>\n","      <td>203</td>\n","    </tr>\n","    <tr>\n","      <th>Social Media</th>\n","      <td>208</td>\n","      <td>212</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["offer_dropped        No  Yes\n","sourcing_channel            \n","Company Website     204  149\n","Consultants         194  264\n","Internal Referrals   85  196\n","Job Portals         284  203\n","Social Media        208  212"]},"execution_count":57,"metadata":{},"output_type":"execute_result"}],"source":["ct = pd.crosstab(data['sourcing_channel'], data['offer_dropped'])\n","ct"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"8jlbrLU2_p15","outputId":"00303c3b-3d63-4c8b-8752-243a4832b6ba"},"outputs":[{"data":{"image/png":"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\n","text/plain":["<Figure size 576x288 with 1 Axes>"]},"metadata":{},"output_type":"display_data"}],"source":["ct = pd.crosstab(data['sourcing_channel'], data['offer_dropped'])\n","ct.plot.bar(stacked=True,figsize = (8,4))\n","\n","plt.title('sourcing_channel and offer_dropped',fontsize = 14)\n","plt.xlabel('sourcing_channel',fontsize = 12)\n","plt.ylabel('offer_dropped',fontsize = 12)\n","\n","plt.legend(title='offer_dropped')\n","plt.ylim(0,max(sum(ct.values)))\n","plt.show()"]},{"cell_type":"markdown","metadata":{"id":"OZYZYtHp_p16"},"source":["Lets understand how different variables are stacked against the target variable Offer dropped.\n","To do this lets plot number of employees who has dropped the offer vs accepted the offer. We plot this with respect to each variable"]},{"cell_type":"markdown","metadata":{"id":"1tVfKSRW_p16"},"source":["#### <font color = brown>Grouped Bar plot with table proportions </font>"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"qJEAFBeO_p16","outputId":"5afbb8e4-fd44-49af-fa69-6c15a8e1834f"},"outputs":[{"data":{"text/plain":["<matplotlib.axes._subplots.AxesSubplot at 0x122a4e550>"]},"execution_count":59,"metadata":{},"output_type":"execute_result"},{"data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAAfMAAADuCAYAAAAtMO66AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjAsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+17YcXAAAgAElEQVR4nO3deUAVVd8H8O9lFzEh2SLN3CIxcEu9oeEuiqApamoimqL0iKYmuEaKOy6otIm2qdDjhlsaoiguAZqW4oIVT+4hXMEF2eGe9w9eJm+AXJQRLn0//+i5c2bmd8/MnR9zZjkKIYQAERER6Sy96g6AiIiIng2TORERkY5jMiciItJxTOZEREQ6jsmciIhIxzGZExER6TgmcyIiIh1nUN0BPIt797KgVvMxeSIiqv309BSwsKhb5jSdTuZqtWAyJyKifz12sxMREek4JnMiIiIdJ2s3+759+/DFF1+gsLAQ3t7eeO+996RpSUlJmDVrllTOyMhA/fr18cMPP8gZEhER1QBCCNy7p0J+fi4AXi79mwJGRiawsLCCQqHQfi65BlpJTU3FiBEjEBkZCSMjIwwfPhyrV69G8+bNS9XNycnB0KFDMX/+fLz55ptaryM9/RGvmRMR6aDMzPsoLCyAuXkDKBTsJC4hhBr379+FgYER6tUz15imp6dAgwZmZc4nWwvGxcVBqVTC3NwcpqamcHV1RVRUVJl1169fjw4dOlQqkRMRke7KyXmEevXMmcj/QaHQQ716FsjJeVSp+WTrZk9LS4OVlZVUtra2RmJiYql6mZmZ2LZtG/bt21fpdZT3FwoREdVsaWkCxsZGlepK/rfQ1zcCIGBlVU/reWRL5mq1WmMjCSHK3Gh79+5Fr1690KBBg0qvg93sRM+fRX0jGBgZV3cYksL8PNx7kF/dYVAlqdVqFBUJ8Hp52dRqNVSqTI3PntTNLlsyt7W1xZkzZ6SySqWCtbV1qXqHDx/GxIkT5QqDiKqYgZExzgaPr+4wJO0DNgJgMq+tkpIuYe7cACiVznB27oJVq5bDw+MdvP/+hCpZfv/+PbF/f0yVLKuyfvrpBGJjYzB37vxnXpZsFyucnZ0RHx+PjIwM5OTkIDo6Gi4uLhp1hBC4dOkS2rZtK1cYRESkwxIS4jBs2AgEBMzF8eOxmDp1RpUl8tpEtjNzGxsbTJs2DaNHj0ZBQQGGDBkCJycn+Pj4YMqUKXB0dERGRgYMDQ1hbFxzuuyIiKj6fP75WsTF/QQDAwN069YDu3btgL6+PurXN8eJE8fw66+/wNS0LoyMjPHZZ2uQn5+PVq3ewPTpM3Hw4AH8+OMPyMhIx/jxvujevVep5RcVFWHlyqW4cOE8mjd/DUVFRQCAxYvn4969DNy+fQvr1n2Jo0cPY+/e3dDTU2DECC/06+eOxYvnw9DQEElJl6Cnp49PPlmEV15pjKFDB8LBoRWSk3+Hk1MbzJgxG/r6+ggL+xwJCXEQQo3335+At9/uhhs3rmHBgo8hhBp2dg1Rp06dKmk3WZ8z9/DwgIeHh8ZnGzZskP7foEED/PTTT3KGQEREOuL48Vhcu3YN3333Pe7dy8AHH4xD796usLN7Gf36ueOXX86gW7eeaNOmHfz8JmDVqlDUq1cPa9asRFTUfigUCuTm5iI8fEe56zh69DAyMzOxefM2nDv3Cw4fPihNa9q0GVauXIfffruC6OgofPXVJhQWFmLChDFwcmoDAMjOzsY330Tg2LGjWLNmJVavDkVKym3MmDELHTsqMWfODBw9ehimpnWRnZ2Fr7/egkePHsHX9320a/cm1qxZhXHjJsLZuQuWLFmAqno6XKffzU5ERLXH+fO/olcvV+jr68PS0gotWtgjOTkZdnYva9S7ceM6rl37E5MnF99vlZ+fB2NjYzRu/Crs7Vs+cR2JiefQtWt3KBQKtG3bHi+++PfN1/b2DgCACxfOwcWlG4yNTWBsDCiVzrh4sfhprL59+wMAXFy6YfnyRQCAF19sgE6d3gIA9OjRG+fPn4ORkRF++ukEzp37FQCQk5ON27dv4cqVy3B27iLVjYmJfqY2K8FkTkRENYJardYoCyFQVFRYRr0i2Nu3xLp1XwIAsrIeQaHQQ2xsDExMTCq1Tn19fen/JfOWHUdxd7yBwd9ps+QBrcc/EwLQ19eDWl3ctd6vnzsAID39LszNLaTlKRQKjXU/Kz6tT0RENULr1m1w+PBBqNVq3L2rwuXLF9GihX2peq+80hg3b97AtWtXIYTA0qULceSIdme4rVu3w9GjMRBC4OLFRKhUaaXqODm1QWzsEeTl5SIr6xHi4n5Cq1aOAIBjx47+/79HpK73tLRUXL58EUIIHD16CO3adYCjY2tERe1HYWEhVKo0vP/+e8jNzYGDQyucOHFMWkZV4Zk5ERHVCF279sCFC4nw9h4OAJg+PQDJyX+UqmdsbII5cwKxYMFcFBQUwMHhDfTr54GDBw9UuI4ePXrh/PlfMGrUUDRp0gzW1jal6rz+ugN69XLF+PGjoVar8e67I9G48asAgNTUFIwZMxJ16tTBJ58Ud7ObmtbF5s3f4saNa+jU6S28/XZXAMDlyxcxZsxIAALTpgWgbl0zTJsWgAUL5uGbb8LQtGkz6OlVzdm5bO9mfx740hii58/Kql6Ne878ny/XoJrvzp3rsLVtXN1hVMrixfPRrVtPdO78tsbncjyrXlb7VMtLY4iIiKrLwoWB+N//kkt9vnTpSrz0kl01RCQvJnMiIqp1Pv44qMqXWd6b2qrrDXKP4w1wREREOo7JnIiISMcxmRMREek4JnMiIiIdx2RORESk43g3OxER1Wj1XjCBibFhlS83N68AmQ9zK6yXkvIXhg4dgJCQT9Ghg1L6fMgQD4SGrq8Rj7oxmRMRUY1mYmyIkQHhVb7ciOD3kImKkzlQ/P715csXY9Om/8LUtG6Vx/Ks2M1ORERUAUtLK3To0AmhoWtKTdu06WuMGjUUo0e/i9DQEGlQlueJyZyIiEgLfn5Tcfp0PH7+OUH6LCEhDidPHsfGjZvx9dfhuH37Jnbv3vncY2MyJyIi0kLdumaYOXMeli9fjOzsLADA2bOn0auXK0xMTGBgYID+/Qfg7Nmfn3tssibzffv2wc3NDX369EF4eOnrHX/++Se8vLwwYMAAjBs3Dg8ePJAzHCIiomfSsaNSo7v9n4N9CYEyx2CXm2zJPDU1FSEhIYiIiMDu3buxdetWJCf//dJ7IQQ++OAD+Pj4YO/evWjZsiXCwsLkCoeIiKhKlHS3p6ffRfv2b+Lw4YPIy8tFYWEhDhzYi3bt3nzuMcl2N3tcXByUSiXMzc0BAK6uroiKioKfnx8A4NKlSzA1NYWLiwsAwNfXFw8fPpQrHCIi0lG5eQWICH5PluU+jZLu9unT/eDs/DYyMzMxbtxoFBUVomNHJTw9363iSCsmWzJPS0uDlZWVVLa2tkZiYqJUvnHjBiwtLTFnzhwkJSWhadOm+Pjjjyu1jvLGdSWifxcrq3rVHQJVUlqaHgwMtOsczsnOR052vixxaBNDo0YNsXv3fo3PnJ2dkZDwCwBg/PgJGD9+QpXGpaenV6n9WrZkrlaroVAopLIQQqNcWFiI06dPY8uWLXB0dMSaNWuwbNkyLFu2TOt1pKc/KnW9gojkVRMTp0qVWd0hUCWp1WoUFqqrO4waS61Wl9qv9fQU5Z7EynbN3NbWFiqVSiqrVCpYW1tLZSsrKzRu3BiOjo4AAHd3d40zdyIiItKObMnc2dkZ8fHxyMjIQE5ODqKjo6Xr4wDQtm1bZGRk4MqVKwCAI0eOoFWrVnKFQ0REVGvJ1s1uY2ODadOmYfTo0SgoKMCQIUPg5OQEHx8fTJkyBY6Ojvjss88wb9485OTkwNbWFsHBwXKFQ0REVGsphBA6e9GZ18yJnj8rq3o4Gzy+usOQtA/YWCXXzOUazONpaTsIiK66c+c6bG0bV3cYNVZZ7fOka+a1eqAV/jiJSFtyDebxtCozCAhRrU7m/HH++1jUN4KBkXF1hyEpzM/DvQfyPFJD9G8h1+9am9/n6tXLkZGRjkWL/r4MfPp0AlasWIrvvouoMSOo1epkTv8+BkbGNa4LGGAyJ3oWcv2utfl9+vpOhrf3cJw8eQxdunRFTk4OVq5citmzP64xiRxgMiciIiqXqakpAgLmYunSILRv3xEbN36JLl1c0K7dm7h06SI+/XQ18vLyYG5ugYCAubC1fQkREZtw8OAB6Ovrw8HBETNmzJI9TiZzIiKiJ+jQoRM6dXoLS5YswPXrV7Fhw3fIz89HcPAirFixFtbWNoiLO4ng4CVYvnw1vv9+C3btOgA9PT0sWbIA6el30aCBpawxMpkTERFVwM9vKjw93bFkyUoYG5vgjz9+w19/3UZAwDQAxW85zcvLg6GhIV5/vSV8fEajS5eueO89b9kTOcBkTkREVKG6dc1gZlYPL71kBwAoKlKjUaNX8PXX4f9fLsK9e/cAAMHBa3DxYiISEuIwfbof5s9fgtat28gan6zjmRMREdVGTZo0QXp6Oi5cOA8A2Lt3FxYuDMTdu3fh5TUMzZu/Bh+fD9Cu3Zv488/kCpb27HhmTkREVEnGxiYIClqGtWtXoaAgH2Zm9TB37nxYWlrCzW0Axo0bBROTOnj11Sbo189d9niYzImIqEYrzM/7/8fIqn65lbFjxz6NcuvWbbBx46ZS9UaO9MLIkV7PFFtlMZkTEVGNVvxiF76v4Ul4zZyIiEjHMZkTERHpOCZzIiKqFjo8aKesnqZdmMyJiOi5MzAwQlbWQyb0fxBCICvrIQwMjCo1H2+AIyKi587Cwgr37qnw6NH96g6lxjEwMIKFhVXl5pEpFiIionLp6xvA0vKl6g6j1pC1m33fvn1wc3NDnz59EB5eelzxTz/9FN27d8fAgQMxcODAMusQERHRk8l2Zp6amoqQkBBERkbCyMgIw4cPR6dOndC8eXOpzsWLF7F69Wq0bdtWrjCIiIhqPdmSeVxcHJRKJczNzQEArq6uiIqKgp+fn1Tn4sWLWL9+PW7fvo0OHTpg5syZMDY2liskIiIiiUV9IxgY1ZycU5if9/8vyKk82ZJ5WloarKz+voBvbW2NxMREqZyVlYWWLVvC398fjRs3xqxZs/D5559j2rRpWq+jQQOzKo35ebCyqlfdIdBzxm0uv9raxrX1e9UkZ4PHV3cIkvYBG2Fl9XR/XMiWzNVqNRQKhVQWQmiU69atiw0bNkjl999/H3PmzKlUMk9PfwS1uvzHGmriD0GlyqzuEGo1bnP51dY2rq3fi8qna9tcT09R7kmsbMnc1tYWZ86ckcoqlQrW1tZS+a+//kJcXByGDBkCoDjZGxjw5noiotqq3gsmMDE2rO4waiXZsqezszNCQ0ORkZGBOnXqIDo6GgsXLpSmm5iYYMWKFejUqRMaNmyI8PBw9O7dW65wiIiompkYG2JkQM15aiki+L3qDqHKyPZomo2NDaZNm4bRo0fjnXfegbu7O5ycnODj44MLFy7gxRdfRFBQED744AP07dsXQgiMHTtWrnCIiIhqLVn7tT08PODh4aHx2ePXyV1dXeHq6ipnCERERLUe381ORESk45jMiYiIdByTORERkY5jMiciItJxTOZEREQ6jsmciIhIxzGZExER6TgmcyIiIh3HZE5ERKTjmMyJiIh0HJM5ERGRjmMyJyIi0nFM5kRERDqOyZyIiEjHyToEKtV+9V4wgYmxYXWHQUT0r8Zk/hypCwtgZVWvusOQFObn4d6D/GdahomxIUYGhFdRRM8uIvi96g6BiOi5YzJ/jvQMDHE2eHx1hyFpH7ARwLMlcyKSR036478q/vAnecmazPft24cvvvgChYWF8Pb2xnvvlX3WFBsbi6CgIBw5ckTOcIiIdEZN+uOff/jXfLIl89TUVISEhCAyMhJGRkYYPnw4OnXqhObNm2vUu3v3LpYvXy5XGERERLWe1nez37t3D4cOHUJMTAwyMzMrrB8XFwelUglzc3OYmprC1dUVUVFRperNmzcPfn5+lYuaiIiIJFqdmR86dAhz5szBa6+9BrVajblz52LNmjVQKpXlzpOWlgYrKyupbG1tjcTERI06mzZtgoODA1q3bv1UwTdoYPZU89Hfaso1udqMbSw/trH82MbPx9O2s1bJPCQkBFu2bIG9vT0A4NKlS5g3bx527dpV7jxqtRoKhUIqCyE0yr///juio6Px7bff4s6dO08VfHr6I6jVotzp3PkqplJV3MvyJGzjij1rG9c0NXGbV0Ub18TvVZOwjZ+PJ7Wznp6i3JNYrbrZTUxMpEQOAK1atdJIzGWxtbWFSqV6LEAVrK2tpXJUVBRUKhU8PT0xYcIEpKWlYeTIkdqEQ0RERI/RKpm7uLggLCwM2dnZyMvLw9atW9GiRQs8ePAA9+/fL3MeZ2dnxMfHIyMjAzk5OYiOjoaLi4s0fcqUKTh48CD27NmDsLAwWFtbIyIiomq+FRER0b+IVt3sGzZsQFFREVavXq3x+Z49e6BQKJCUlFRqHhsbG0ybNg2jR49GQUEBhgwZAicnJ/j4+GDKlClwdHSsmm9ARET0L6dVMr906dJTLdzDwwMeHh4an23YsKFUvYYNG/IZcyIioqekVTJXq9X46quvcPz4cRQWFqJz587w9fWFgQFfIEdERFTdtLpmvmrVKiQkJMDb2xtjx47Fr7/+yhe9EBER1RBanVqfOHECO3fuhKFh8ehY3bp1w4ABA2QNjIiIiLSj1Zm5EEJK5ABgZGSkUSYiIqLqo1Uyf/3117FkyRLcuHEDN2/exNKlS/Haa6/JHRsRERFpQatk/sknn+Dhw4cYPnw4hg0bhoyMDHz88cdyx0ZERERa0Oqa+fr167Fs2TK5YyEiIqKnoNWZeWxsrMxhEBER0dPS6sy8YcOGeP/999GuXTvUrVtX+nzs2LGyBUZERETa0SqZm5ubAyh+E5y+vj7q1ePIN0RERDWFVt3s48ePx++//45jx47hyJEjuHnzJiZPnix3bERERKQFrZL5nDlzMGzYMJw/fx7nzp2Dq6sr5s6dK3dsREREpAWtknlOTg7effddGBoawsjICF5eXrh7967csREREZEWtErmTZs2xS+//CKVf//9dzRs2FC2oIiIiEh7Wt0A99dff8HLywv29vYwMDDA5cuXYWVlJQ1vum/fPlmDJCIiovJplcxnzJghdxxERET0lLRK5h07dpQ7DiIiInpKWl0zf1r79u2Dm5sb+vTpg/Dw8FLTDx06BA8PD/Tv3x+zZs1Cfn6+nOEQERHVSrIl89TUVISEhCAiIgK7d+/G1q1bkZycLE3Pzs5GUFAQvvnmG+zfvx95eXnYtWuXXOEQERHVWrIl87i4OCiVSpibm8PU1BSurq6IioqSppuamuLIkSOwtLRETk4O0tPT8cILL8gVDhERUa2l1TXzp5GWlgYrKyupbG1tjcTERI06hoaGOHbsGAICAmBtbY0uXbpUah0NGphVSaz/ZlZWfDWv3KqijfMLimBkqF8F0dRO3I/lxzZ+Pp62nWVL5mq1GgqFQioLITTKJbp27YpTp05h9erVmD9/PlatWqX1OtLTH0GtFuVO585XMZUq85nmZxtX7FnbGChu55EBpe87qQ4Rwe9VdwilVFUbU/nYxs/Hk9pZT09R7kmsbN3stra2UKlUUlmlUsHa2loq379/HydPnpTKHh4e+O233+QKh4iIqNaSLZk7OzsjPj4eGRkZyMnJQXR0NFxcXKTpQgj4+/vjr7/+AgBERUWhXbt2coVDRERUa8nWzW5jY4Np06Zh9OjRKCgowJAhQ+Dk5AQfHx9MmTIFjo6OWLhwISZOnAiFQoHmzZtjwYIFcoVDRERUa8mWzIHirvOSV76W2LBhg/T/Xr16oVevXnKGQEREVOvJ+tIYIiIikh+TORERkY5jMiciItJxTOZEREQ6jsmciIhIxzGZExER6TgmcyIiIh3HZE5ERKTjmMyJiIh0HJM5ERGRjmMyJyIi0nFM5kRERDqOyZyIiEjHMZkTERHpOCZzIiIiHcdkTkREpOOYzImIiHScrMl83759cHNzQ58+fRAeHl5q+uHDhzFw4EAMGDAA//nPf/DgwQM5wyEiIqqVZEvmqampCAkJQUREBHbv3o2tW7ciOTlZmv7o0SPMnz8fYWFh2Lt3L+zt7REaGipXOERERLWWbMk8Li4OSqUS5ubmMDU1haurK6KioqTpBQUF+OSTT2BjYwMAsLe3R0pKilzhEBER1VoGci04LS0NVlZWUtna2hqJiYlS2cLCAr179wYA5ObmIiwsDF5eXpVaR4MGZlUT7L+YlVW96g6h1mMby49tLD+28fPxtO0sWzJXq9VQKBRSWQihUS6RmZmJSZMm4fXXX8egQYMqtY709EdQq0W507nzVUylynym+dnGFXvWNgbYzhVhG8uPbfx8PKmd9fQU5Z7EytbNbmtrC5VKJZVVKhWsra016qSlpWHkyJGwt7fH4sWL5QqFiIioVpMtmTs7OyM+Ph4ZGRnIyclBdHQ0XFxcpOlFRUXw9fVFv379MHfu3DLP2omIiKhisnWz29jYYNq0aRg9ejQKCgowZMgQODk5wcfHB1OmTMGdO3dw+fJlFBUV4eDBgwCAN954g2foRERElSRbMgcADw8PeHh4aHy2YcMGAICjoyOuXLki5+qJiIj+FfgGOCIiIh3HZE5ERKTjmMyJiIh0HJM5ERGRjmMyJyIi0nFM5kRERDqOyZyIiEjHMZkTERHpOCZzIiIiHcdkTkREpOOYzImIiHQckzkREZGOYzInIiLScUzmREREOo7JnIiISMcxmRMREek4WZP5vn374Obmhj59+iA8PLzcegEBAYiMjJQzFCIiolpLtmSempqKkJAQREREYPfu3di6dSuSk5NL1fH19cXBgwflCoOIiKjWky2Zx8XFQalUwtzcHKampnB1dUVUVJRGnX379qFnz57o16+fXGEQERHVegZyLTgtLQ1WVlZS2draGomJiRp1xo8fDwA4e/asXGEQERHVerIlc7VaDYVCIZWFEBrlqtCggVmVLu/fyMqqXnWHUOuxjeXHNpYf2/j5eNp2li2Z29ra4syZM1JZpVLB2tq6SteRnv4IarUodzp3voqpVJnPND/buGLP2sYA27kibGP5sY2fjye1s56eotyTWNmumTs7OyM+Ph4ZGRnIyclBdHQ0XFxc5FodERHRv5ZsydzGxgbTpk3D6NGj8c4778Dd3R1OTk7w8fHBhQsX5FotERHRv45s3ewA4OHhAQ8PD43PNmzYUKresmXL5AyDiIioVuMb4IiIiHQckzkREZGOYzInIiLScUzmREREOo7JnIiISMcxmRMREek4JnMiIiIdx2RORESk45jMiYiIdByTORERkY5jMiciItJxTOZEREQ6jsmciIhIxzGZExER6TgmcyIiIh3HZE5ERKTjmMyJiIh0nKzJfN++fXBzc0OfPn0QHh5eanpSUhIGDx4MV1dXzJ07F4WFhXKGQ0REVCvJlsxTU1MREhKCiIgI7N69G1u3bkVycrJGHX9/fwQGBuLgwYMQQmDbtm1yhUNERFRryZbM4+LioFQqYW5uDlNTU7i6uiIqKkqafvv2beTm5qJNmzYAgMGDB2tMJyIiIu0YyLXgtLQ0WFlZSWVra2skJiaWO93KygqpqamVWoeenqLCOpYWdSu1TLkZvdCgukPQoE0bVoRt/GRV0cZAzWpntvHzUZPamW38fDypnZ80TSGEEHIE9MUXXyAvLw9Tp04FAGzbtg0XL15EUFAQAODs2bNYtWoVIiIiAADXrl2Dr68vz86JiIgqSbZudltbW6hUKqmsUqlgbW1d7vS7d+9qTCciIiLtyJbMnZ2dER8fj4yMDOTk5CA6OhouLi7S9JdffhnGxsY4e/YsAGDPnj0a04mIiEg7snWzA8WPpq1fvx4FBQUYMmQIfHx84OPjgylTpsDR0RFXrlzBvHnz8OjRI7Rq1QpLly6FkZGRXOEQERHVSrImcyIiIpIf3wBHRESk45jMiYiIdByTORERkY5jMiciItJxTOZEREQ6TqeT+aNHj7BgwQK4u7tj4MCB8PLywqVLl6o7rEr54osvsHjxYql89OhR2NvbS8/fA8D06dMRGRlZ7jJCQ0MRGhqq9Tp9fHyQmpqKmzdvYs6cOU8XeCVU13Z6vF1mz56N27dvP9Vyjh49im+++aYqQyuXvb19hXW8vLxkj6NHjx64deuWxmenTp1C27ZtMXDgQAwcOBAeHh7o0aMHvv/++wqXN3v2bPTs2RM//PBDlcYZGRmJWbNmVekyq2q9s2bNeuLvFtBs03feeQd9+/bFlClT8OjRo0rFo80+UdY2rQmioqIwePBgDBgwAB4eHti4ceNTLefChQuYO3fuE+uUt03s7e0xbtw4jc8yMjLQqlWrSh1bb926hR49egAA1q5di5iYGK3nfVayvZtdbmq1Gj4+PujUqRN2794NAwMDJCQkwMfHB/v374eFhUV1h6gVpVKJRYsWSeWTJ0+iS5cuOHnyJNq3bw+g+NW3M2fOrLJ1btiwAUDxgeTmzZtVttyy1JTtdOrUKUyaNOmp5r148WIVR/NsTp8+XW3rfuONN7B582apnJSUhCFDhsDDwwNmZmblzrdr1y4kJibyPRJl+GebTpkyBevXr8dHH32k9TKqc594FqmpqVi+fDkiIyNhYWGBrKwseHl5oUmTJujZs2elluXo6AhHR8enjuXq1au4f/8+zM3NAQDR0dF44YUXnnp5H3744VPP+zR0NpmfOnUKKSkpmDJlCvT0ijsYlEolli5dCrVaDQD48ssvsXfvXujr66Nz587w9/dHSkoKJk2ahKZNmyI5ORkODg5o27Ytdu3ahQcPHuCzzz5Ds2bN0KNHD/Tt2xdxcXEAgCVLlsDBwQGnT59GSEgIcnNz8fDhQ8yePRu9evXCrFmzYGZmhkuXLiE1NRWTJk3CoEGD0KtXL3z11Vdo0qQJsrOz0a9fP0RHR8PY2BhA8Q5469YtZGdnw9TUFPHx8Vi2bBkWLlyIDz/8EDdv3oSZmRlsbGxw9+5dBAYG4s6dO1AoFPjoo5rMIiUAABcVSURBVI/g7OwMAEhMTMTQoUORnZ2NYcOGwdvbG3fu3MGMGTOQnZ0NPT09zJs3D23atEGPHj2wadMmLFq0CLdu3cKCBQvwySefICwsDD/++COKiorQpUsX+Pv7Q6F4tsEVKtpO5W0jPz8/tGjRAklJSWjQoAHWrl2LunXrYs6cOfjjjz8AACNHjsSwYcMwa9YsdOzYEYMHDwZQ/Ff2b7/9JsUQFhaGtLQ0TJgwAeHh4UhISMA333yD3Nxc5OfnY8mSJWjXrh28vLzg6OiIs2fPIiMjA/PmzcPLL7+M//73vwAAOzs72NnZYcWKFQCA+vXrY9WqVXjxxRefqY3Ka7f169fDxMQE//vf/2Bvb4+VK1ciODgYADB06FBs374dx48fx7p161BYWIiGDRti4cKFsLCwQI8ePeDk5ISkpCSsWLECgYGBpdrT3NwcW7ZswZ49e5CTkwNDQ0OsWrUKTZs21TrO27dvo06dOjAyMkJRURGCg4Nx+vRpFBUVYfDgwRgzZgx8fX0hhMDQoUPx9ddf48SJE/juu++gVqvRqlUrfPLJJzA2NoZSqcQbb7wBlUqFgIAAhISEQK1Wo0WLFpg+fTrmzJmDzMxMpKWlYdCgQaUOlsuXL8dPP/0EPT099OrVC35+flW6Tcpz9epVBAYG4v79+zA1NcXcuXPh5OQEAIiNjcWWLVtQUFCADz74AG5ubhUur2PHjjh58iSA4l6hNWvWQK1Wo1GjRggKCoKlpaXG9n3rrbcA/L1PVLRNr1y5gsDAQBQWFsLY2BhLly7Fq6++WvUNo4V79+6hoKAAubm5AIC6deti2bJl0vHx3LlzWLx4MfLy8mBhYYGgoCA0btwYSUlJCAwMRG5uLurXr4+VK1fi+vXr+PTTT7F58+Zyj9NP0rNnT8TExMDT0xNAcY9B7969pemJiYlYunQpcnNzYWFhgQULFqBRo0a4fPmy1CPw+uuvS/UfPy6FhIQgPj4eDx48gLW1NUJCQmBpaVmlbQmhozZu3CgmTpxY7vTY2FgxdOhQkZ2dLQoKCoSvr6/YsmWLuHnzprC3txeXLl0SRUVFolevXmLlypVCCCFCQ0PF4sWLhRBCdO/eXYSGhgohhIiJiRHu7u5CCCEmT54skpOThRBCxMXFSZ/PnDlTTJo0SajVanHlyhXRsWNHIYQQa9euFWvWrBFCCLFr1y4RGBhYKtYJEyaI+Ph4cePGDTFixAghhBA9evQQGRkZIjIyUixatEgIIcTUqVPF4cOHhRBCpKamip49e4rMzEyxbt06MXDgQJGVlSUyMzNF7969xeXLl0VoaKjYsGGDEEKIY8eOiY0bN0rf7ebNmyIhIUGMGjVKmj558mRRWFgoioqKxPTp08Xu3bsrv2H+4UnbSZttJIQQfn5+YtOmTeLUqVPCx8dHCCHEnTt3hL+/vxCiuO137twpLfe1114TQgixbt06sW7dOo3vXFRUJEaPHi3S09OFEEJs375dim/UqFFSW8fExIhBgwaVWs6oUaPE+fPnhRBChIWFiRMnTjxzGz2uJPaEhATRpk0bkZKSIoqKioSnp6eIiYnRqJOeni4GDBgg7t+/L4QQ4vvvvxdz5syRvm9Jm5TXnpmZmcLb21vk5OQIIYRYs2aNCAoK0mivx5XENGDAANG7d2/RsWNHMXnyZKk9IiIixJIlS4QQQuTl5YlRo0aJn3/+WSPm33//XYwYMULk5uYKIYRYuXKl+Oyzz6Q6CQkJ0rrat28vHj58KIQo3o8iIyOFEEI8fPhQtG3bVqSnp4udO3eKmTNnilu3bgk3NzchhBDZ2dniww8/lNYhh5L1CiGEp6enOHjwoBBCiF9//VV069ZN5OXliZkzZ4rx48eLgoICcefOHdG5c2eRlpamsZzHf4NCCJGVlSXGjh0rvvjiC3H37l3RpUsXaTts2LBBTJ48WQihuX2F+Lt9tdmms2bNEgcOHBBCCBEZGSl27dpV5e1TGYGBgcLBwUF4enqK4OBgkZSUJIQo3oe6d+8u7V8HDhwQgwcPFkII4ebmJo4cOSKEECI8PFwsW7ZMoy2fdJx+vN1KvPbaa+Ls2bPS8UWlUglvb2/pt5+Xlyc8PDzE7du3hRBCHD9+XHh7ewshhHB3dxcnT54UQgjx6aefiu7du2us69q1a8LPz08UFRUJIYTw9/cXX331VRW2YDGdPTPX09OT/norS0JCAvr37486deoAADw9PbF792507doVlpaWcHBwAFA84EvJX7Z2dnYa15SGDRsGoPha06xZs5CRkYEVK1bg6NGjiIqKwvnz55GVlSXV79y5MxQKBV577TXcv38fQPE47WPHjsWHH36IXbt2Yfr06aVifeutt/DLL7/g6tWr6Ny5M4Dis9ezZ8/izJkz6NOnD4DiMeL//PNPrFu3DgBQWFgodZO7ubnB1NQUANC9e3ecPn0ab731FiZPnoykpCR07doVo0aNKre94uPjkZiYKJ3d5ubmws7Ortz62nrSdnrSNmrQoIG0jVq0aIEHDx6gRYsWuHr1KsaNGwcXFxcEBAQ8VTyfffYZjhw5gqtXr+L06dNSjwEAvP3229I6S7bh43r27Ak/Pz/06tULPXv2lLaXHFq0aAFbW1sAQLNmzfDgwQON6efPn0dKSgpGjx4NoPiSRv369aXprVu3lv5fVnuamZlh1apV2L9/P65du4YTJ06gZcuWT4yppEs4Pz8f/v7+MDMzk85C4+PjkZSUhISEBABAdnY2fvvtN7z55pvS/KdOncL169el31ZBQYEU1z9jbtKkCerVqwcAGDduHBISEvDVV1/hjz/+QEFBAXJycqS6NjY2MDY2xvDhw9G9e3fMmDHjiceHqpKVlYUbN25Iv9E2bdqgfv36+PPPPwEAgwYNgoGBAWxsbNCmTRucP3++1BnixYsXMXDgQADFv2mlUomxY8ciLi4OTk5OaNiwIQDg3XffRVhYmDTf421VQptt2rVrVwQFBeHEiRPo0aMHunfvXnUN8hQWLFiA//znPzh58iROnjyJYcOGYeXKlXj11VfxwgsvSPtXv379EBgYiNu3b0OlUklxjxw5EkDxvlXiScfp8rRt2xZXr15FZmYmoqKi4Orqirt37wIoHtXz5s2b+OCDD6T6jx49QkZGBtLS0qTjwODBg7Fz506N5TZu3BgzZ87E9u3bcfXqVZw7dw6vvPLKM7RY2XQ2mb/xxhuIiIiAEEKjK3j16tVwdnaWutofV1hYCAClrtvp6+uXuQ4Dg7+bR61WQ19fHyNHjkSnTp3QqVMnvPXWW5gxY4ZUp+Tg8Xg8DRs2hJ2dHaKjo5Genl7mD1CpVGL16tUwMjKCj48PgOI/DM6fP4/ExESpC0etVuO7776TrumkpaWhQYMGOHz4cKlYDQwM0L59e+zfvx+xsbE4cOAAdu3aVe6NXEVFRfD29sbYsWMBAA8fPiy3XSrjSdspPj4egwYN0qhfso0ePxArFAoIIWBhYYH9+/fjp59+wrFjxzBo0CDs379fmg4UJ4cnycrKwpAhQzBgwAB06NAB9vb2CA8Pl6aXtQ0fN2bMGHTv3h1Hjx7FihUrkJiYqPEDr0pltcHjioqK0K5dO3z55ZcAgLy8PI2D1uPzl7WslJQUeHl5YdSoUXBxcYGlpSWSkpK0is3IyAiLFi2Cq6srDhw4ADc3NxQVFcHf319KbBkZGahbV3Ps6qKiIvTr1w/z5s0DULw9ioqKpOkmJiZl/n/ZsmW4efMm3N3d0atXL8TFxWm0h4GBAbZv347Tp0/j+PHjGD58ODZv3owmTZpo9X20cebMGTRq1Ag2NjYQQkBfX7/UNgEAIYT0nR7/DanVahgaGpaq/89r5o/X/+dyS34fAMr8Y0Wbbdq3b1+0bdsWR48exbfffovY2FiN+3aep9jYWGRnZ8PNzQ2enp7w9PTEtm3bsGPHjjJPfEra+/HfZ15eHtLS0jTqPek4XR6FQoHu3bsjJiYGBw8exNq1a6Vjg1qtRsOGDbFnzx4Axfvx3bt3S/0uyzpmXrx4ER999BHGjBkDV1dX6OnplbnfPCudvZv9zTffRIMGDfDpp59KP5wTJ04gMjISzZs3h1KpxP79+5Gbm4vCwkLs3LkTSqWyUuvYv38/AODQoUNo1qwZhBC4du0aPvzwQ7i4uCAmJkbjQFQeT09PLFq0CAMGDChzur29PVJSUvDHH39IN3C89dZbOHbsGCwsLKQzbqVSKY3/npycDA8PD+ns5ODBg8jPz8eDBw8QGxsLpVKJ4OBg7N27F4MGDUJgYCAuX76ssV59fX3p4KBUKrFnzx5kZWWhsLAQkyZNwsGDByvVXmV50nby9vau1DaKiYmBv78/unXrhnnz5sHU1BQpKSkwNzdHcnIyAODw4cNlzquvr4+ioiJcu3YNCoUCvr6+6NSpEw4dOlThNny8nYYOHYqsrCyMGTMGY8aMKdWmz0NJPK1bt8a5c+dw9epVAMDnn38uXVPXxoULF9C4cWOMGTMGjo6OOHz4sFb7c4l69eph8uTJCA4ORm5uLpRKJbZt24aCggJkZWVh5MiROHfunMY8JW2enp4OIQTmz5+P7777rsJ1/fTTTxg3bhz69euHq1evIjU1VSPZXb58GaNGjUKHDh0wc+ZMNGvWTGqXqrJz505p//rtt9/QqFEjmJmZoWHDhoiOjgZQfI337t27aNGiBYDiY4gQArdv38bFixcrdYNW69atcf78eam3cOvWrejUqVOZdUv2CW226dSpU3HhwgUMHz4cH374YbXswyVMTEywatUq6TsKIZCUlISWLVuiadOmuH//PhITEwEABw4cgJ2dHV5++WXY2NhI9xXs2bMHa9eulZZ5//79pzpOA8Vn/xERETAyMtK4F6Zp06Z48OABzpw5A6B4X5gxYwYsLCxgZ2eH2NhYACjzaY2ff/4ZHTt2xIgRI/Dqq68iNja2Ur8zbensmblCocDnn3+OpUuXwt3dHQYGBrCwsEBYWBgsLS3RvXt3JCUlwdPTE4WFhejSpQtGjRqFO3fuaL2OX375BTt27ECdOnWwbNkymJubY8iQIejfvz8MDAygVCqRm5uL7OzsJy6nT58++Pjjj6WutLK+S7NmzaBWq6UuXwsLCxgaGko3uAHAvHnzEBgYCA8PDwBAcHCwdAexnZ0dhg8fjry8PEycOBHNmjWDl5cXPvroI0RGRkJfXx/Lly/XWG+zZs2QmZkJf39/rFixAleuXMGwYcNQVFSEt99+u9RZ89N40nZycHBASkqK1tvIxcUF0dHR6N+/P4yNjTFgwADY29tjxIgRmDp1Kjw8PKBUKmFlZVVq3m7dumHChAnYsGEDWrZsiX79+kGhUKBLly4ajwGWpSRBWFpaYvr06Zg1axYMDAxgampaLWc0PXv2xMCBAxEZGYklS5Zg6tSpUKvVsLGxkW7O00bnzp3x/fffw83NDUIIdOjQQbq5UFtDhw7F5s2b8c0332D8+PG4fv06Bg0ahMLCQgwePLhU8nn99dfh5+cHb29vqNVqtGzZEhMmTKhwPRMnTkRAQABMTExga2uLN954Q+OSmIODA9q0aQN3d3fUqVMH7dq1q/IhlSdMmICAgABs2bIFtra2WLNmDYDiLt358+cjNDQUhoaGCA0NlXr/TE1NMXjwYBQWFiIoKKhSN0taWloiKCgIfn5+KCgogJ2dncZjrI8r2Se2bdtW4Tb19fXF3Llz8dlnn8HQ0BDz589/ugapAkqlEn5+fvD19ZV61d5++21MmjQJRkZGCAkJwcKFC5GTk4P69esjJCQEwN9tvmLFClhYWCA4OFj64+1pj9NA8WUSlUqFoUOHanxuZGSEtWvXSjfjmZmZScfTFStWYPbs2VizZg3atGlTaplubm7w8/OTjtv/3HerCkdNK0fJHd8l16uelhACx48fx/fffy91hxIREVUlnT0z1xVLlizB0aNHpWe7iYiIqhrPzImIiHSczt4AR0RERMWYzImIiHQckzkREZGOYzIn+hfx8fGRnsl/HiIjIzFx4sTntr6y3Lp1C23btq3WGIjkxrvZif5F+FQFUe3EZE5UTbKysjB79mxcv34denp6aNWqFYKCgrB9+3Zs3rwZenp6sLS0xMcff4wmTZpg1qxZaNGihTTu8uPlklG0fvvtN0yfPh3NmzdHYGAgMjIyoKenJ43Y1aNHD6xduxbZ2dkICQlBo0aN8Mcff6CwsBALFixA+/btkZGRgdmzZ+PGjRswNzeHlZUVWrRogcmTJz/x+6xfvx67du2CgYEBGjdujGXLlgEAVCoVJkyYgJSUFOjr62PVqlVo1qwZzp07hxUrViA/Px8qlQrOzs5YsmQJbt26hTFjxqBr1644f/48Hj58CH9/f/Tu3RuhoaHSu7lv374tvSjH2toaqampCAoKQkpKCgoKCtC/f3/4+vrKvh2JagJ2sxNVk0OHDiErKwt79uzBjh07AADbt2/Hxo0bsWnTJuzduxfu7u6YNGmSVu9ybtGiBX788Uf07t0b06dPR9++fbF//36EhYVh9erVePTokUb9xMREvP/++9i9e7c0TCMALFq0CM2bN8ePP/6ItWvX4pdffqlw3TExMYiMjMTWrVvxww8/oGHDhtiyZQsA4ObNm5g7dy727duHN998E1999RUAYNOmTZgyZQq2b9+O/fv348iRI9LY8Tdv3kSXLl2wY8cOfPTRR1iyZIm0rjNnzmDt2rWIiopCnTp1pCFq/f394enpicjISOzYsQNxcXE4cOBAhbET1QZM5kTVpH379khOToaXlxfCwsLg7e2N69evw83NTXrt5+DBg5GamqrV6x9LRie7f/8+rly5Ir2S8qWXXsLhw4elV/+WsLOzk0bUcnBwkEZlO3bsGN59910AgLW1Nfr27VvhuuPj49G3b19p1LbZs2dLA9A4OTmhcePGAICWLVsiIyMDQPHgKZmZmfjyyy+xYMEC5OXlSa/cNDQ0RNeuXaXYHh/BrmPHjtJ3KYk7OzsbP//8M9auXYuBAwdi2LBhSElJwZUrVyqMnag2YDc7UTVp1KgRDh06hFOnTiEhIQFjx46FtbW1NAxriZLRsv45QtM/R4grGZCnZAS9x0eW+vPPP0sNafv4qGSPL9vAwEBjPY8PEVsefX19jfU9fPgQDx8+1Ijnn+sZNWoU7O3t8fbbb6Nfv344f/68NM3Q0FBa7z9HsCsrbrVaDSEE/vvf/0pD6mZkZMDY2Bj37t2rMH4iXcczc6JqEhERgdmzZ6NLly7w9/dHly5d0KNHDxw4cEA6e925cyfMzc3RuHFjWFhYSN3QqampOH36dJnLNTMzQ6tWrbB7924AxcNijhgxApmZmVrF1bVrV6nb/969ezh8+HC5Q8KWcHZ2xqFDh6Su/NDQUHz77bfl1n/48CEuXLiAGTNmoE+fPrhz5w5u3LhR5tDF2jAzM0ObNm2kIX4fPnyIESNGICYm5qmWR6RreGZOVE3eeecdnD59Gm5ubqhTpw5eeukleHl5wcLCQhpV7MUXX8T69euhp6cHLy8vzJgxA66urmjYsOETh4tdtWoVFixYgM2bN0OhUGDx4sVljiZXltmzZ2PevHnw8PCAubk57OzsNM6Gy9K1a1ckJydjxIgRAIDmzZtj4cKF0tCg//TCCy9gwoQJGDRoEExNTWFjY4N27drh+vXraNSokVZx/tPKlSuxcOFCeHh4ID8/H+7u7hgwYIAsI1QR1TR8NzsRaQgPD4eDgwPatm2L/Px8jBw5EpMnT5auYRNRzcMzcyLSUHJWrVarUVBQgL59+6Jr164YOXIksrKyypwnPDy81A12RPT88MyciIhIx/EGOCIiIh3HZE5ERKTjmMyJiIh0HJM5ERGRjmMyJyIi0nFM5kRERDru/wDBFBfpe0blPwAAAABJRU5ErkJggg==\n","text/plain":["<Figure size 576x252 with 1 Axes>"]},"metadata":{},"output_type":"display_data"}],"source":["plt.rcParams[\"figure.figsize\"] = (8,3.5)\n","y='prop'\n","prop_data = (data['offer_dropped']\n","           .groupby(data['sourcing_channel'])\n","           .value_counts(normalize=True)\n","           .rename(y)\n","           .reset_index())\n","sns.barplot(x=\"sourcing_channel\", y=\"prop\", hue=\"offer_dropped\", data=prop_data)"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"_j5_z1rP_p17","outputId":"e64ce940-383c-48d0-bcd3-c14734038df4"},"outputs":[{"name":"stdout","output_type":"stream","text":["     sourcing_channel offer_dropped      prop\n","0     Company Website            No  0.577904\n","1     Company Website           Yes  0.422096\n","2         Consultants           Yes  0.576419\n","3         Consultants            No  0.423581\n","4  Internal Referrals           Yes  0.697509\n","5  Internal Referrals            No  0.302491\n","6         Job Portals            No  0.583162\n","7         Job Portals           Yes  0.416838\n","8        Social Media           Yes  0.504762\n","9        Social Media            No  0.495238\n"]}],"source":["print(prop_data)"]},{"cell_type":"markdown","metadata":{"id":"5-LkU10Q_p19"},"source":["#### <font color = brown>Chi Square Analysis for \"Test of Independence\" </font>"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"GuodVCXr_p19","outputId":"cd318081-6a66-4d90-9627-094eceac6276"},"outputs":[{"name":"stdout","output_type":"stream","text":["===Chi2 Stat===\n","75.4696901092181\n","===Degrees of Freedom===\n","4\n","===P-Value===\n","1.5851371352330645e-15\n","===Contingency Table===\n","[[172.17358679 180.82641321]\n"," [223.38669335 234.61330665]\n"," [137.05602801 143.94397199]\n"," [237.53126563 249.46873437]\n"," [204.85242621 215.14757379]]\n"]}],"source":["from scipy import stats\n","ct = pd.crosstab(data[\"sourcing_channel\"],data[\"offer_dropped\"])\n","chi2_stat, p_val, dof, ex = stats.chi2_contingency(ct)\n","\n","print(\"===Chi2 Stat===\")\n","print(chi2_stat)\n","print(\"===Degrees of Freedom===\")\n","print(dof)\n","print(\"===P-Value===\")\n","print(p_val)\n","print(\"===Contingency Table===\")\n","print(ex)"]},{"cell_type":"markdown","metadata":{"id":"YCWPzytb_p1-"},"source":["__Insight: sourcing_channel is very significant variable__"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"rsvKn-QK_p1_","outputId":"b9579fbd-b1c6-4ed0-e288-548512936aec"},"outputs":[{"data":{"text/plain":["Index(['age', 'career_growth', 'days_offered', 'distance_from_home',\n","       'education_level', 'flexi_work', 'gender', 'jhi', 'marital_status',\n","       'offer_dropped', 'percent_hike', 'sourcing_channel',\n","       'timely_communication', 'total_rounds'],\n","      dtype='object')"]},"execution_count":62,"metadata":{},"output_type":"execute_result"}],"source":["data.columns"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"l2ubWg27_p1_","outputId":"52fcc500-1c2b-415f-8f3d-e7d4561746cb"},"outputs":[{"data":{"text/plain":["(158.41178842879063,\n"," 2.51572950763228e-36,\n"," 1,\n"," array([[627.23861931, 658.76138069],\n","        [347.76138069, 365.23861931]]))"]},"execution_count":63,"metadata":{},"output_type":"execute_result"}],"source":["ct = pd.crosstab(data[\"career_growth\"],data[\"offer_dropped\"])\n","stats.chi2_contingency(ct)"]},{"cell_type":"markdown","metadata":{"id":"ZxJMCjd2_p2B"},"source":["#### <font color =brown> Age vs Renege </font>"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"Fzf0eeqo_p2B","outputId":"7fcb070d-372d-41e7-9cd8-35a694b35e6b"},"outputs":[{"data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAAfAAAAEbCAYAAAAlL9anAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjAsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+17YcXAAAgAElEQVR4nO3deXRU9f3/8ddkgQQiaxOkfBGLkICEzYgQVgEbIzFlF8rmkU2WgoRFAQERsCxSkSgonioitoIkBCNgvmgQ0rBLLZaCVAQCAYwhkITsy3x+f/Bz2nzZl8lwh+fjnJzj3T6f943cvObzmTtzbcYYIwAAYCkeri4AAADcPAIcAAALIsABALAgAhwAAAsiwAEAsCACHAAACyLAgTuke/fuCgoK0nfffefqUu6ILl26aM6cOVfd/tZbbykoKKjMT6NGjRQSEqL+/ftr27Zt5VcscA/ycnUBgDs4cuSIjhw5ogYNGigmJkbNmjVzdUnlwsfHR6tWrXIsl5aW6syZM3rvvfc0duxYxcbGqlGjRi6sEHBfjMCBO2DDhg1q1KiR+vbtq40bNyovL8/VJZULDw8PtWjRwvETEhKiyMhIvfXWWyopKVF8fLyrSwTcFgEO3KbS0lJ9/vnn6tChg5566inl5+friy++KLPP999/ryFDhqhFixbq2rWrPvvsM/32t7/VW2+95dgnIyNDL774oh577DG1bNlSo0aN0qlTp67Zd05OjubNm6fOnTsrODhYbdq00UsvvaTs7GzHPkFBQVq/fr2ioqLUsmVLtW7dWq+99ppKSkoc+6Snp2v8+PEKCQlRhw4dtGHDhtv6nfj5+V22Li8vT3PnzlXbtm3VrFkzDR48WIcOHXJsX79+vVq3bq1du3ape/fuCg4OVrdu3ZSYmFimnZSUFI0ZM0YtW7bUo48+qilTpuj8+fNl9vniiy/09NNPq1mzZurTp4+++uorBQUFac+ePY59Dh48qGeffVbNmzdXmzZtNHfuXOXn59/WeQPliQAHbtOOHTuUnp6uyMhI1apVS6GhoVq3bp1j+7lz5zRkyBAVFhbqjTfe0IgRI/Taa6/p7Nmzjn0KCgo0ZMgQ7d+/XzNmzNCiRYt07tw5DRo0SFlZWVfte9KkSdq6dasmTZqk999/X0OHDtXGjRu1fPnyMvv98Y9/VI0aNbR8+XINHDhQH330kT799FNJl16ADBs2TAcPHtTcuXM1depURUdHKy0t7YbOv6SkxPFTWFioo0ePatq0afLy8lJERIQkyRij0aNHa9OmTZowYYKWLl2qChUqaPDgwTp58qSjrdzcXE2fPl0DBw7UihUrVL16dUVFRSkzM9PxuxwwYIDOnDmjRYsW6dVXX9U//vEPDRs2TEVFRZKkpKQkRUVFqWnTplq2bJnatm2rSZMmlan56NGjGjRokGw2m958801NnjxZmzdv1oQJE27onIG7ggFwWyZOnGh69OjhWN6wYYMJDAw0R48eNcYY88Ybb5iQkBCTlZXl2CchIcEEBgaa6OhoY4wxn3zyiWncuLHjGGOMuXjxonn00UfNW2+9dcV+CwoKzHPPPWe2b99eZv2oUaNMz549HcuBgYFm+PDhZfbp0aOHef75540xxnz11VcmMDDQfPvtt47tBw8eNIGBgebVV1+96nlHR0ebwMDAy34aNWpkevXqZXbs2OHYNykpyQQGBpZZV1xcbMLCwszUqVONMcbExsaawMBAs2nTJsc+hw8fNoGBgSYhIcEYY8zixYtNSEiIycjIcOxz8uRJ07hxYxMXF2eMMaZfv35m0KBBZWqdM2eOCQwMNLt37zbGGBMVFWW6dOliCgsLHfvs27fPBAYGmr179171nIG7CSNw4Dbk5OQoMTFRv/3tb5Wdna3s7Gy1adNGvr6+jlH4nj179Nhjj6lKlSqO45544gl5ef3nHtI9e/aoXr16qlevnmM06+Pjo5CQEO3evfuKfVesWFEffPCBOnbsqNTUVCUnJ2vlypX68ccfVVxcXGbf5s2bl1muVauW4336v//976patapatGjh2N6kSRPVqVPnuufv4+OjmJgYxcTE6L333lOjRo3UoEEDRUdHq23btmXOz9fXV61atXKcnyS1b9/+svP77zruv/9+SXJMbe/Zs0ctWrRQlSpVHO3Url1bDz30kHbt2qXCwkIdOHBAXbt2LdNmeHh4meU9e/aoXbt28vDwcLTTokUL+fn5adeuXdc9b+BuwF3owG1ISEhQfn6+li5dqqVLl5bZtmHDBk2cOFEXLlxQgwYNymzz9PRU9erVHcuZmZk6duyYmjRpclkfDz744FX7T0xM1Pz583Xq1ClVr15dwcHB8vHxkd1uL7Ofr69vmWUPDw+Z//8gwuzs7DK1/MLf3/+q/f53O02bNnUsBwcH6+mnn9bw4cMVGxurSpUqOc4vPz9fwcHBl7Xh7e1dZtnHx6dM+5Ic55OZmakDBw5c8ffk7++vrKws2e121ahRo8y2mjVrllnOzMzU2rVrtXbt2svaSU9Pv+Y5A3cLAhy4DZ999pmaNWumyZMnl1l/9OhRzZkzR4mJiQoICLjsJiu73e54X1eS7rvvPjVq1Ejz5s27rI8KFSpcse8TJ07ohRdeUM+ePfXxxx87RqsvvPCCfvzxxxs+h2rVqikjI+Oy9f9d342qWbOmpk2bpilTpig6OlpTp06VdOn8atasqRUrVtx0m//Nz89PHTt21Pjx4y/bVrlyZdWsWVPe3t6X/b7/77Kfn5+6du2q3//+95e1c6UXM8DdiCl04BadOXNG+/btU/fu3dW6desyP/3795e/v79iYmLUqlUr7d27Vzk5OY5jk5KSykxzP/LII0pNTVWdOnXUtGlTNW3aVMHBwfrwww+v+oUohw4dUnFxsUaOHOkI77y8PO3fv98xur4RrVu31sWLF8tMHR8/frzMzWU343e/+50eeeQRffzxxzp27JgkKSQkROfPn1elSpUc59e0aVN9/vnnN/VRs5CQEB07dkxBQUGONgIDA/X2229r//798vT0VIsWLbR169Yyx/3fO9l/aSc4ONjRTu3atfWnP/1JP/zwwy2dN1DeCHDgFm3YsEE2m01hYWGXbfP09NRTTz2lnTt3qnfv3vLw8NDIkSP19ddfKzY2VjNmzJAk2Ww2SVKfPn1UrVo1DR06VJs3b9bOnTs1YcIEbd68+apfhNK4cWN5enrq9ddf165du7R582YNGTJE586du6mPQ7Vr106tWrXSlClTtGHDBm3ZskVjx469bGr7ZkydOlUlJSVauHChJKlz585q2rSpRo4cqbi4OO3evVtz5szRqlWr9NBDD91wu88995wuXryo4cOH66uvvtL27ds1cuRI7d692zE9P3bsWO3du1czZsxQcnKy3n77bX388ceS/jMlP2bMGB08eFAvvPCCtm/fri+//FIjRozQ999/r4cffviWzxsoTwQ4cIvi4+P1yCOPKCAg4IrbIyMjZbfbFRsbqw8++EB2u13jx4/X8uXLNW3aNEmXpn2lS1O6f/nLX1S/fn3Nnj1bY8aM0ZkzZ7R8+XJ16tTpiu3/5je/0cKFC3XkyBGNHDlSixcvVnBwsF555RWdPXv2hj8GZrPZ9M4776hDhw567bXX9Morr6hnz5639Q1qzZs3V7du3bRt2zYlJyfL09NT77//vtq1a6fXX39dI0eO1L59+zR//nz179//htv99a9/rb/+9a/y9fXVlClTFBUVJbvdrpUrV6px48aSpNDQUC1atEj79u3TqFGjlJSU5PgY2S/vyQcHB2vVqlW6cOGCxo8fr5dfflm1atXS6tWrVatWrVs+b6A82czNzLUBuGnffvutCgoKFBoa6lh3/PhxhYeHa/ny5ZfdMY3b89VXX+mBBx5QYGCgY93atWs1e/Zs7dmzp8ynAQAr4yY2wMlOnjypl19+WRMnTlTTpk117tw5vfvuu3rwwQfVvn17V5fndr7++mslJydr0qRJql27tn788UctWbJEv/vd7whvuBVG4EA5+PDDD7V27VqdPn1alStXVrt27TRlyhSma50gNzdXf/rTn5SYmKiMjAwFBAQoMjJSY8eOveod/YAVEeAAAFgQN7EBAGBBBDgAABZEgAMAYEGWuwv9woVc2e28bQ8AcG8eHjZVr175qtstF+B2uyHAAQD3PKbQAQCwIAIcAAALIsABALAgAhwAAAsiwAEAsCACHAAACyLAAQCwIAIcAAALIsABALAgAhwAAAsiwAEAsCACHAAACyLAAQCwIAIcAAALIsABALAgpwb41q1b1atXLz311FOaN2+eJGnnzp2KjIxUWFiYlixZ4szuAQBwW04L8FOnTumVV17R8uXLFR8fr0OHDmn79u2aPn26li9frs2bN+vgwYPavn27s0oAAMBtOS3Av/zyS3Xr1k3333+/vL29tWTJEvn6+qpevXqqW7euvLy8FBkZqYSEBGeVAACA2/JyVsMpKSny9vbWqFGjdPbsWT3++ONq2LCh/P39HfsEBAQoLS3NWSUAAOC2nBbgpaWl+uabb7R69WpVqlRJo0ePlo+Pj2w2m2MfY0yZ5RtRs6bfnS4VAADLcVqA/+pXv1JoaKhq1KghSXriiSeUkJAgT09Pxz7p6ekKCAi4qXYzMnJkt5s7WisAAHcbDw/bNQetTnsPvHPnzkpOTlZ2drZKS0v1t7/9TeHh4Tp+/LhSUlJUWlqqjRs3qmPHjs4qAQAAt+W0EXjz5s01fPhwDRgwQMXFxWrXrp1+//vfq379+ho3bpwKCwvVqVMnhYeHO6sEAADcls0YY6n5aKbQAQD3ApdNoQMAAOchwAEAsCACHAAACyLAAQCwIAIcAAALIsABALAgAhwAAAsiwAEAsCACHAAACyLAAQCwIAIcAAALIsABALAgAhwAAAsiwAEAsCACHAAACyLAAQCwIAIcAAALIsABALAgAhwAAAsiwAEAsCACHAAACyLAAQCwIAIcAAALIsABALAgAhwAAAsiwAEAsCACHAAACyLAAQCwIAIcAAALIsABALAgAhwAAAsiwAEAsCACHAAACyLAAQCwIC9nNj548GCdP39eXl6XupkzZ45Onjypd955RyUlJXr22Wc1cOBAZ5YAAIBbclqAG2N04sQJff31144AT0tLU1RUlNavX68KFSqof//+at26tRo0aOCsMgAAcEtOC/Bjx45JkoYOHarMzEw988wzqly5stq0aaNq1apJkp588kklJCToD3/4g7PKAADALTntPfDs7GyFhoZq2bJl+vDDD7VmzRqdOXNG/v7+jn0CAgKUlpbmrBIAAHBbThuBt2zZUi1btnQs9+nTR/Pnz9fo0aMd64wxstlsN9VuzZp+d6xGAACsymkB/s0336i4uFihoaGSLoV1nTp1lJ6e7tgnPT1dAQEBN9VuRkaO7HZzR2sFAOBu4+Fhu+ag1WlT6BcvXtSiRYtUWFionJwcxcXF6fXXX9euXbt0/vx55efna8uWLerYsaOzSgAAwG05bQTeuXNnHThwQD169JDdbteAAQMUEhKiqKgoDRkyRMXFxerTp4+aNWvmrBIAAHBbNmOMpeajmUIHANwLXDaFDgAAnIcABwDAgghwAAAsiAAHAMCCCHAAACyIAAcAwIIIcAAALIgABwDAgghwAAAsiAAHAMCCCHAAACzIaQ8zgfPs2JGk5OTtri7jpmRlZUqSqlat5uJKblz79p3Urh1Py8N/cO2VH66/62MEjnKRlZWlrKwsV5cB3HO49twXTyNDuVi4cK4k6aWXZrq4EuDewrVnXTyNDAAAN0SAAwBgQQQ4AAAWRIADAGBBBDgAABZEgAMAYEEEOAAAFkSAAwBgQQQ4AAAWRIADAGBBBDgAABZEgAMAYEEEOAAAFkSAAwBgQQQ4AAAWRIADAGBB1w3w3Nxcvfrqq3r22WeVmZmpWbNmKTc3tzxqAwAAV3HdAJ83b56qVKmijIwMVaxYUTk5OZo1a1Z51AYAAK7iugF++PBhRUVFycvLS76+vlq8eLEOHz5cHrUBAICr8LreDh4eZTO+tLT0snVW9te/fqRTp1JcXYbbO3ny0u944cK5Lq7EvdWtW08DBgxxdRkAysF1A7xVq1Z6/fXXVVBQoL/97W/6y1/+otatW5dHbeXi1KkUHfnhqDx9qrm6FLdmL/WUJB09dc7Flbiv0oJMV5cAoBxdN8AnT56s9957T/fdd5+WLFmiDh06aMyYMTfcwcKFC3XhwgUtWLBAhw8f1ssvv6zc3Fw9+uijevXVV+Xldd0SnM7Tp5oq1evq6jKA25KXkujqEgCUo+vOhXt7e2vs2LFat26d1q9fr6ioKFWsWPGGGt+1a5fi4uIcy1OmTNGsWbP0v//7vzLG6NNPP731ygEAuIddd/jbpUsX2Ww2x7LNZpOvr68aNmyoqVOnKiAg4IrHZWZmasmSJRo1apS+//57nT59WgUFBWrRooUkqVevXoqOjtaAAQPu0KkAAHDvuG6AP/HEE8rNzdXAgQPl4eGhmJgY5ebmKigoSLNmzdK77757xeNmzZqlqKgonT17VpL0888/y9/f37Hd399faWlpd+g0AFgRN5E6HzeQlg9X3EB63QD/5ptvtH79esfyjBkz1KdPH82fP1+xsbFXPGbdunWqXbu2QkNDHcfa7fYyI3ljTJnlG1Wzpt9NH3Mt3t6ed7Q9wJW8vT3l73+fq8u4YT/9lKoTR7/X/X6uvxfGXVWSXZJU8NNRF1fivn7KKXHJtXfdqyY3N1c5OTny87sUnDk5OcrPz7/mMZs3b1Z6erq6d++urKws5eXlyWazKT093bHPuXPnrjr9fi0ZGTmy281NH3c1xcWld6wtwNWKi0uVnn7R1WXcsOLiUt3v56XnmtVwdSnALVv53XmnXHseHrZrDlqvG+C9e/fWM888o/DwcNntdn355Zfq27evVq9erfr161/xmJUrVzr+e/369dq7d6/mz5+vp59+Wvv371dISIg+++wzdezY8RZOCQAAXDfAR44cqcaNGyspKUleXl4aPXq0Vq1apdmzZ6tnz5431dnixYs1Y8YM5eTkqEmTJhoyhC+cAADgVtzQG0/NmjXT4cOH9fHHHysmJkaDBw9WkyZNbqiDXr16qVevXpKkRo0aKSYm5tarBQAAkq4T4MeOHdOqVasUHx+vOnXqqLCwUFu3btV991nnJhkAANzRVb/IZeTIkRo0aJC8vb310UcfaePGjapcuTLhDQDAXeCqAX7o0CE1adJEDRs2VL169STplj72BQAA7ryrBvi2bdvUs2dPbdy4Ue3bt9f48eNVWFhYnrUBAICruGqAe3l5qVu3blq9erXWr1+vgIAAFRYWKiwsTJ988kl51ggAAP6PG3qwd4MGDTRjxgwlJSVp2LBhPIQEAAAXu6EA/4Wvr6/69etX5gljAACg/N1UgAMAgLsDAQ4AgAUR4AAAWBABDgCABd3zD+HNyspUaUGm8lISXV0KcFtKCzKVlXXPX9LAPYMROAAAFnTPv1yvWrWa0rNLVKleV1eXAtyWvJREVa1azdVlACgnjMABALCge34EDsB1srIydSGnRCu/O+/qUoBb9lNOiapnZZZ7v4zAAQCwIEbgAFymatVqqph/Ts81q+HqUoBbtvK78/Jxwf0njMABALAgAhwAAAsiwAEAsCACHAAACyLAAQCwIAIcAAALIsABALAgAhwAAAsiwAEAsCACHAAACyLAAQCwIAIcAAALIsABALAgAhwAAAsiwAEAsCACHAAAC3JqgC9dulTdunVTRESEVq5cKUnauXOnIiMjFRYWpiVLljizewAA3JaXsxreu3evdu/erfj4eJWUlKhbt24KDQ3V9OnTtXr1atWuXVvPP/+8tm/frk6dOjmrjBtSWpCpvJREl9bg7uwlBZIkDy8fF1fivkoLMiX9ytVlACgnTgvwxx57TB999JG8vLyUlpam0tJSZWdnq169eqpbt64kKTIyUgkJCS4N8Lp167ms73vJyZMpkqQH6hIwzvMr/j0D9xCnBbgkeXt7Kzo6Wh988IHCw8P1888/y9/f37E9ICBAaWlpzizhugYMGOLS/u8VCxfOlSS99NJMF1eCu81POSVa+d15V5fhtnKK7JIkvwrc8uQsP+WU6EEX9OvUAJek8ePHa8SIERo1apROnDghm83m2GaMKbN8I2rW9LvTJaIceHt7SpL8/e9zcSW4mwQFNXT824BzpB87JkmqXbe+iytxX/dJql+/frn/fXNagP/4448qKipS48aN5evrq7CwMCUkJMjT8z8Xa3p6ugICAm6q3YyMHNnt5k6XCycrLi6VJKWnX3RxJbib9OjR39UluL1fZr8mTpzu4krc353+++bhYbvmoNVpcyqpqamaMWOGioqKVFRUpMTERPXv31/Hjx9XSkqKSktLtXHjRnXs2NFZJQAA4LacNgLv1KmTvvvuO/Xo0UOenp4KCwtTRESEatSooXHjxqmwsFCdOnVSeHi4s0oAAMBtOfU98HHjxmncuHFl1oWGhio+Pt6Z3QIA4Pa4LREAAAsiwAEAsCACHAAACyLAAQCwIAIcAAALIsABALAgAhwAAAsiwAEAsCACHAAACyLAAQCwIAIcAAALIsABALAgAhwAAAsiwAEAsCACHAAACyLAAQCwIJsxxri6iJuRkZEju91SJd9xO3YkKTl5u6vLuCknT6ZIkh54oJ6LK7lx7dt3Urt2HV1dBu4iXHvlh+tP8vCwqWZNv6tu9yrHWnAPq1q1qqtLAO5JXHvuixE4AAB3oeuNwHkPHAAACyLAAQCwIAIcAAALIsABALAgAhwAAAsiwAEAsCACHAAACyLAAQCwIAIcAAALIsABALAgAhwAAAsiwAEAsCACHAAACyLAAQCwIAIcAAALIsABALAgpwb422+/rYiICEVERGjRokWSpJ07dyoyMlJhYWFasmSJM7sHAMBtOS3Ad+7cqeTkZMXFxWnDhg3617/+pY0bN2r69Olavny5Nm/erIMHD2r79u3OKgEAALfltAD39/fX1KlTVaFCBXl7e+uhhx7SiRMnVK9ePdWtW1deXl6KjIxUQkKCs0oAAMBtOS3AGzZsqBYtWkiSTpw4oS+++EI2m03+/v6OfQICApSWluasEgAAcFtezu7ghx9+0PPPP68XX3xRnp6eOnHihGObMUY2m+2m2qtZ0+8OVwgAgPU4NcD379+v8ePHa/r06YqIiNDevXuVnp7u2J6enq6AgICbajMjI0d2u7nTpQIAcFfx8LBdc9DqtCn0s2fPauzYsVq8eLEiIiIkSc2bN9fx48eVkpKi0tJSbdy4UR07dnRWCQAAuC2njcDff/99FRYWasGCBY51/fv314IFCzRu3DgVFhaqU6dOCg8Pd1YJAAC4LZsxxlLz0UyhAwDuBS6bQgcAAM5DgAMAYEEEOAAAFkSAAwBgQQQ4AAAWRIADAGBBBDgAABZEgAMAYEEEOAAAFkSAAwBgQQQ4AAAWRIADAGBBBDgAABZEgAMAYEEEOAAAFuTl6gJuloeHzdUlAADgdNfLO5sxxpRTLQAA4A5hCh0AAAsiwAEAsCACHAAACyLAAQCwIAIcAAALIsABALAgAhwAAAsiwAEAsCACHAAACyLAcUelpqYqKChIO3bsKLO+S5cuSk1NdVFVgPuaM2eOxo8fX2ZdcnKyunbtqpycHBdVhfJAgOOO8/b21syZM/njAZSDSZMm6eDBg0pMTJQk5eXlafbs2frjH/8oPz8/F1cHZyLAcccFBASobdu2Wrhw4WXb3n33XXXr1k2RkZFasGCBSktLXVAh4D4qV66sefPmae7cucrLy1N0dLS6dOmi1q1b68CBA+rfv7969uypYcOG6fTp05KkP//5z4qMjFTPnj01e/Zs154AbhkBDqeYOnWqkpOTy0ylJyUlaevWrYqNjVVcXJxSUlK0Zs0aF1YJuIe2bduqffv2mjZtmnbs2KGJEyeqqKhIM2bM0Jtvvqm4uDgNHjxYs2bNUlFRkT744APFxcUpNjZW+fn5Sk9Pd/Up4BZY7nGisAY/Pz/NnTtXM2fOVHx8vCRp9+7dioiIkK+vrySpd+/e2rBhgwYOHOjKUgG3MHXqVD3++ONatmyZfHx8dPjwYaWmpur555+XJBljVFhYqAoVKig4OFh9+vRR165dNWLECPn7+7u4etwKAhxO0759+zJT6Xa7/bJ9SkpKyrsswC35+fmpSpUqqlOnjiSptLRUDz74oOLi4hzLGRkZkqQVK1bo22+/VVJSkoYOHao33nhDjz76qMtqx61hCh1O9ctU+s8//6w2bdpo06ZNKigoUElJiWJjY9WmTRtXlwi4pQYNGig9PV1///vfJUlr167Viy++qJ9//lkRERFq1KiRJkyYoDZt2ujf//63i6vFrWAEDqf6ZSp92LBhevzxx5Wdna3evXurpKRE7du316BBg1xdIuCWfHx89Oabb+q1115TUVGRqlSpogULFiggIEC9e/dWr169VKlSJdWvX189e/Z0dbm4BTZjjHF1EQAA4OYwhQ4AgAUR4AAAWBABDgCABRHgAABYEAEOAIAF8TEy4C70ySef6JNPPlFJSYlsNpsefvhhRUVF6de//rWkS0+bmjlzpmrWrKmVK1dqxIgRunjxol544QWFhYXdUp9dunSRt7e3fHx8ZIyRMUbdunXTiBEj5OV1d/2pePrppzVz5ky1bt3a1aUALnN3XZUAtHDhQn3//fdasWKFateuLbvdrvj4ePXr10/r1q3T/fffr02bNqlv374aM2aM9u3bp4yMDH355Ze33ffixYvVtGlTSZeeajV58mTNnz9fM2fOvO22AdxZBDhwF/npp5+0Zs0abdu2TVWrVpUkeXh4qEePHjp48KBWrFihOnXqKDExURUrVtS//vUv/fvf/1ZaWpq6d++utWvX6tChQ1q8eLHy8/Pl4eGhP/zhD+rcubPWr1+vmJgY5efny8/PT6tXr75mLZUqVdKsWbP0xBNPKCoqSlu2bLns+GXLlmnTpk3y9PTUb37zG82cOVP+/v4aPHiwHn74Ye3fv18XLlxQ9+7dNX78eKWmpmrw4MHq0KGDDhw4IGOMZs2a5fgaz/PGrJUAAAQFSURBVHfeeUdbtmyR3W5XnTp19Morr6hWrVo6evSopk+frvz8fNWvX195eXlO/38B3PUMgLtGQkKC6dWr1xW3JSYmmsjISGOMMS+99JL585//bIwxZvfu3SYiIsIYY0xmZqYJCwszp06dMsYY89NPP5mOHTua06dPm9jYWNOqVStz8eLFK7bfuXNn89133122vnXr1ubAgQOXHR8TE2P69etncnNzjTHGREdHm6FDhxpjjBk0aJAZMWKEKSoqMllZWebJJ580W7duNadOnTKBgYEmPj7eGGPMtm3bTLt27UxRUZGJi4szEyZMMMXFxcYYY9asWWOGDx9ujDGme/fu5tNPPzXGGPPNN9+YoKAgs3v37pv51QJuhxE4cJe52gNeioqKZLPZrnnsP/7xD6Wnp2vs2LGOdTabTUeOHJEkBQUFyc/P76bqsdlsjifI/ffxSUlJjq/jlKQhQ4bo3XffVVFRkSSpX79+8vb2lre3t8LDw5WcnKyGDRuqatWqioyMlCR16tRJnp6eOnLkiL7++mv985//VO/evSVdevhNfn6+Lly4oCNHjqhHjx6SpJCQEDVs2PCmzgFwRwQ4cBdp0aKFUlJSlJ6eftkjHvfs2aOWLVte8/jS0lI99NBDWrdunWNdWlqaatSooc8//9wRtjfq9OnTysvL0wMPPKB//vOfZY632+1lXlDY7fYyLz7++8Y3Y4w8PC596MXT07NMH3a7XZ6enrLb7Ro+fLgGDBgg6dILlqysrDJtXKlt4F7Fx8iAu0itWrU0ePBgTZw4UWlpaY71sbGx2rJli0aMGHHN4395AbBv3z5J0uHDh/Xkk0+WaetGZWdna+7cuRo4cKAqVqx42fYOHTooNjbW8X706tWr1apVK1WoUEGSFB8fL7vdrqysLH3xxRfq0qWLJOn8+fNKSkqSJG3dulXe3t4KDAxU+/btFRMTo5ycHEnS0qVL9eKLL6p69epq0qSJ40XJL+/7A/c6XsYCd5lJkyZp3bp1Gj16tIqKilRUVKSmTZtqzZo1jmc9X02NGjUUHR2tRYsWqbCwUMYYLVq0SP/zP/+jvXv3XrfvyZMny8fHR56eniotLVVYWJhGjRp1xX379Omjs2fPqm/fvrLb7apXr54WL17s2F5QUKA+ffooNzdXAwYMUGhoqFJTU1WxYkV99tlnWrx4sXx8fLRs2TJ5enqqb9++SktL0zPPPCObzabatWtrwYIFkqQ33nhD06ZN05o1a/TAAw+ofv36N/EbBdwTTyMDcMcNHjxYAwcOVHh4eJn1qampioyM1LfffuuiygD3wRQ6AAAWxAgcAAALYgQOAIAFEeAAAFgQAQ4AgAUR4AAAWBABDgCABRHgAABY0P8Dv+JFakDal/8AAAAASUVORK5CYII=\n","text/plain":["<Figure size 576x288 with 1 Axes>"]},"metadata":{},"output_type":"display_data"}],"source":["plt.figure(figsize = (8,4))\n","g = sns.boxplot(x=\"offer_dropped\",y=\"age\", data=data)\n","plt.title('Age and Renege',fontsize = 16)#plt.title('Job Level and Attrition rate',fontsize = 16)\n","plt.ylim ([15,65])\n","plt.ylabel(\"Age\",fontsize=12)\n","#plt.xticks([0,1,2,3,4],['Low','Medium','High','Very High','Executive'])\n","plt.xlabel(\"Offer Dropped\",fontsize=12)#plt.xlabel(\"JobLevel\",fontsize=12)\n","plt.show()"]},{"cell_type":"markdown","metadata":{"id":"fgN45bC8_p2C"},"source":["__Insight: Age does not seem to be a reason of offer drop__"]},{"cell_type":"markdown","metadata":{"id":"1Q5v-xQ3_p2C"},"source":["#### <font color = brown> Statistical Approach: two sample t-test </font>"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"z8_NPC7p_p2C","outputId":"d76a2f82-34f6-4571-d2bc-0e0eab730010"},"outputs":[{"data":{"text/plain":["Ttest_indResult(statistic=-2.867305108363797, pvalue=0.004183251918114724)"]},"execution_count":67,"metadata":{},"output_type":"execute_result"}],"source":["from scipy import stats\n","stats.ttest_ind(data.loc[data[\"offer_dropped\"] == 'Yes',\"age\"],data.loc[data[\"offer_dropped\"] == 'No', \"age\"])"]},{"cell_type":"markdown","metadata":{"id":"tQklE27S_p2D"},"source":["__Insight: \"age\" is not very significant variable w.r.t target__"]},{"cell_type":"markdown","metadata":{"id":"48lyYZHX_p2E"},"source":["Similarly let's see if days_offered has an effect on offer_dropped"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"u2r5iPEd_p2E","outputId":"81c8671e-82d4-4f30-906c-0fbbe54e91f2"},"outputs":[{"data":{"image/png":"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\n","text/plain":["<Figure size 576x288 with 1 Axes>"]},"metadata":{},"output_type":"display_data"}],"source":["plt.figure(figsize = (8,4))\n","g = sns.boxplot(x=\"offer_dropped\",y=\"days_offered\", data=data_final)\n","plt.title('days_offered and offer_dropped',fontsize = 16)\n","plt.ylim ([0,200])\n","plt.ylabel(\"days_offered\",fontsize=12)\n","plt.xlabel(\"offer_dropped\",fontsize=12)\n","plt.show()\n"]},{"cell_type":"markdown","metadata":{"id":"6RrIAytb_p2E"},"source":["__Insight: This calls for interview process optimization as delayed process may lead candidates to apply for jobs elsewhere due to lack of clarity__\n","\n"]},{"cell_type":"markdown","metadata":{"id":"lNQLgDF9_p2F"},"source":["#### <font color = brown>Statistical Approach: 2 sample t test </font>"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"MKHXNFu1_p2F","outputId":"594ca2ce-00b9-41bd-831e-c78c88b7b73a"},"outputs":[{"data":{"text/plain":["Ttest_indResult(statistic=9.863591428137518, pvalue=1.931849482631004e-22)"]},"execution_count":69,"metadata":{},"output_type":"execute_result"}],"source":["from scipy import stats\n","stats.ttest_ind(data.loc[data[\"offer_dropped\"] == 'Yes',\"days_offered\"],data.loc[data[\"offer_dropped\"] == 'No', \"days_offered\"])"]},{"cell_type":"markdown","metadata":{"id":"pnWQg6mQ_p2F"},"source":["__Insight: \"days_offered\" is very significant variable w.r.t target__"]}],"metadata":{"celltoolbar":"Slideshow","kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.7.3"},"colab":{"provenance":[]}},"nbformat":4,"nbformat_minor":0}