first commit

Drop_Columns.txt

@@ -0,0 +1 @@
+["sex", "high_blood_pressure", "diabetes", "smoking", "anaemia"]

app.py

@@ -0,0 +1,11 @@
+import streamlit as st
+import eda # python file
+import prediction # python file
+
+navigation = st.sidebar.selectbox('Page Navigation: ',('EDA','Predict Patients Conditions'))
+
+if navigation == 'EDA':
+    eda.run()
+else:
+    prediction.run()
+

eda.py

@@ -0,0 +1,104 @@
+import streamlit as st
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+import plotly.express as px
+from PIL import Image
+
+st.set_page_config(
+    page_title='Heart Failure Prediction based on Ensamble Classifier: Random Forest Classifier and Adaptive Boost Classifier',
+    layout = 'wide',
+    initial_sidebar_state='expanded'
+)
+
+def run():
+    # membuat title
+    st.title('Heart Failure Prediction')
+
+    # membuat sub header
+    st.subheader ('Exploratory Data Analysis of the dataset.')
+
+    # Menambahkan Gambar
+    image = Image.open('heart_failure.jpg')
+    st.image(image,caption = 'Heart Failure ilustration')
+
+    # Menambahkan Deskripsi
+    st.write('This page created by Ahmad Luay Adnani')
+    st.write('# Dataset')
+
+
+    # show dataframe
+    df = pd.read_csv('phase1_ftds_018_rmt.csv')
+    st.dataframe(df)
+
+    # DEATH_EVENT
+    st.write('# Exploaratory Data Analysis ')
+    st.write('## Number of Death Event ')
+    # death_event  value count
+    death_event = df.DEATH_EVENT.value_counts().to_frame()
+    death_event = death_event.reset_index()
+    death_event['index'] = death_event['index'].replace({0:'No',1:'Yes'})
+    death_event
+
+    # Plot PieChart with Plotly
+    fig = px.pie(death_event,values='DEATH_EVENT', names='index')
+    # fig.update_traces(text = death_event['DEATH_EVENT'].value_counts(), textinfo = 'label+percent+value')
+    fig.update_layout(title_text = "Death Event", title_x = 0.5)
+    st.plotly_chart(fig)
+    st.write('Number of deaths after the following days are different, where **Non-Death are 36% greater than Death**. This will be keep in mind if there is any imbalance data or not. But first, the death_event--as the target--will be compared with other variables so we can get the conclusion for the skewness and handling imbalance data.')
+
+    # Gender Distribution
+    st.write('### Gender Distribution ')
+    # gender value count
+    sex = df.groupby(by=['sex','DEATH_EVENT']).aggregate(Number_of_DEATH_EVENT=('DEATH_EVENT','count'))
+    sex = sex.reset_index()
+    sex['sex'] = sex['sex'].replace({0:'Female',1:'Male'})
+    sex
+
+    # plotting bar plot
+    fig = px.bar(sex, x="sex", y="Number_of_DEATH_EVENT", color="DEATH_EVENT",
+             orientation="v",hover_name="sex"        
+                
+             )
+    fig.update_layout(title_text = "Gender Distribution", title_x = 0.5)
+    st.plotly_chart(fig)
+    st.write('From the visualization above, Male patients who have smoking habits have a higher chance of dying during follow up periods than any other conditions.')
+
+    
+    # Male Patients Condition
+    st.write('## Male Patients Condition ')
+    # male patients deceased during the follow up period 
+    df_male = df.loc[(df['sex']==1)&
+                    (df['DEATH_EVENT']==1)]
+    df_male.head()
+
+    # Create Bar Charts
+    sns.set(font_scale=2)
+    fig, ax = plt.subplots(1,4, sharex=True, figsize=(40,25))
+    sns.countplot(ax=ax[0],x=df_male['anaemia'], palette='winter')
+    ax[0].set_title('Male patients with anemia')
+    sns.countplot(ax=ax[1],x=df_male['diabetes'], palette='winter')
+    ax[1].set_title('Male patients with diabetes')
+    sns.countplot(ax=ax[2],x=df_male['high_blood_pressure'], palette='winter')
+    ax[2].set_title('Male patients with high blood pressure')
+    sns.countplot(ax=ax[3],x=df_male['smoking'], palette='winter')
+    ax[3].set_title('Male patients with habit of smoking')
+    st.pyplot(fig)
+    st.write('From the table and visualization above, it can be seen that the number of male patients with heart failure is more than female patients. **Where about 32% die during the follow-up period**. Further data exploration is necessary to find out the condition of male patients.')
+
+    # 
+    st.write('## Comparison between Death Event with other variables ')
+    # Creating new dataframe for the histogram
+    sns.set(font_scale=1)
+    output = 'DEATH_EVENT'
+    cols = [f for f in df.columns if df.dtypes[f] != "object"]
+    f = pd.melt(df, id_vars=output, value_vars=cols)
+
+    # Creating histogram
+    g = sns.FacetGrid(f, hue=output, col="variable", col_wrap=4, sharex=False, sharey=False )
+    g = g.map(sns.histplot, "value", kde=True).add_legend()
+    st.pyplot(g)
+    st.write('Based on the histogram above, we can see that the distribution of Not Death is still dominating that Death. However, we should check wherer variable time looks different than the others, where Death is high with time between 0-100 days. From here we should check the skewness of time as well.')
+
+if __name__ == '__main__':
+    run()

h8dsft_p1g3_Ahmad Luay Adnani_inference.csv

@@ -0,0 +1,11 @@
+,age,anaemia,creatinine_phosphokinase,diabetes,ejection_fraction,high_blood_pressure,platelets,serum_creatinine,serum_sodium,sex,smoking,time,DEATH_EVENT
+12,65.0,0.0,56.0,0.0,25.0,0.0,237000.0,5.0,130.0,0.0,0.0,207.0,0.0
+52,67.0,0.0,213.0,0.0,38.0,0.0,215000.0,1.2,133.0,0.0,0.0,245.0,0.0
+108,75.0,0.0,582.0,0.0,20.0,1.0,265000.0,1.9,130.0,1.0,0.0,4.0,1.0
+136,72.0,1.0,943.0,0.0,25.0,1.0,338000.0,1.7,139.0,1.0,1.0,111.0,1.0
+188,65.0,0.0,198.0,1.0,35.0,1.0,281000.0,0.9,137.0,1.0,1.0,146.0,0.0
+205,55.0,0.0,7861.0,0.0,38.0,0.0,263358.03,1.1,136.0,1.0,0.0,6.0,1.0
+206,75.0,1.0,81.0,0.0,38.0,1.0,368000.0,4.0,131.0,1.0,1.0,10.0,1.0
+219,53.0,1.0,707.0,0.0,38.0,0.0,330000.0,1.4,137.0,1.0,1.0,209.0,0.0
+228,62.0,0.0,61.0,1.0,38.0,1.0,155000.0,1.1,143.0,1.0,1.0,270.0,0.0
+237,75.0,0.0,582.0,0.0,40.0,0.0,263358.03,1.18,137.0,1.0,0.0,107.0,0.0

inference.ipynb

@@ -0,0 +1,756 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "# Save and Load Model\n",
+    "import pickle\n",
+    "import json"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\luay9\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python39\\site-packages\\sklearn\\base.py:299: UserWarning: Trying to unpickle estimator MinMaxScaler from version 1.2.2 when using version 1.2.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:\n",
+      "https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations\n",
+      "  warnings.warn(\n",
+      "C:\\Users\\luay9\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python39\\site-packages\\sklearn\\base.py:299: UserWarning: Trying to unpickle estimator StandardScaler from version 1.2.2 when using version 1.2.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:\n",
+      "https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations\n",
+      "  warnings.warn(\n",
+      "C:\\Users\\luay9\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python39\\site-packages\\sklearn\\base.py:299: UserWarning: Trying to unpickle estimator ColumnTransformer from version 1.2.2 when using version 1.2.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:\n",
+      "https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations\n",
+      "  warnings.warn(\n",
+      "C:\\Users\\luay9\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python39\\site-packages\\sklearn\\base.py:299: UserWarning: Trying to unpickle estimator NearestNeighbors from version 1.2.2 when using version 1.2.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:\n",
+      "https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations\n",
+      "  warnings.warn(\n",
+      "C:\\Users\\luay9\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python39\\site-packages\\sklearn\\base.py:299: UserWarning: Trying to unpickle estimator DecisionTreeClassifier from version 1.2.2 when using version 1.2.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:\n",
+      "https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations\n",
+      "  warnings.warn(\n",
+      "C:\\Users\\luay9\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.9_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python39\\site-packages\\sklearn\\base.py:299: UserWarning: Trying to unpickle estimator RandomForestClassifier from version 1.2.2 when using version 1.2.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:\n",
+      "https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations\n",
+      "  warnings.warn(\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Loading Model Files\n",
+    "\n",
+    "with open('rf_gridcv_best.pkl', 'rb') as file_1:\n",
+    "  rf_gridcv_best = pickle.load(file_1)\n",
+    "\n",
+    "with open('Drop_Columns.txt','r') as file_2:\n",
+    "  Drop_Columns = json.load(file_2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "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>anaemia</th>\n",
+       "      <th>creatinine_phosphokinase</th>\n",
+       "      <th>diabetes</th>\n",
+       "      <th>ejection_fraction</th>\n",
+       "      <th>high_blood_pressure</th>\n",
+       "      <th>platelets</th>\n",
+       "      <th>serum_creatinine</th>\n",
+       "      <th>serum_sodium</th>\n",
+       "      <th>sex</th>\n",
+       "      <th>smoking</th>\n",
+       "      <th>time</th>\n",
+       "      <th>DEATH_EVENT</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>65.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>56.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>25.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>237000.00</td>\n",
+       "      <td>5.00</td>\n",
+       "      <td>130.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>207.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>67.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>213.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>38.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>215000.00</td>\n",
+       "      <td>1.20</td>\n",
+       "      <td>133.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>245.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>75.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>582.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>20.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>265000.00</td>\n",
+       "      <td>1.90</td>\n",
+       "      <td>130.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>72.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>943.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>25.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>338000.00</td>\n",
+       "      <td>1.70</td>\n",
+       "      <td>139.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>111.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>65.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>198.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>35.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>281000.00</td>\n",
+       "      <td>0.90</td>\n",
+       "      <td>137.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>146.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>55.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>7861.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>38.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>263358.03</td>\n",
+       "      <td>1.10</td>\n",
+       "      <td>136.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>75.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>81.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>38.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>368000.00</td>\n",
+       "      <td>4.00</td>\n",
+       "      <td>131.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>53.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>707.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>38.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>330000.00</td>\n",
+       "      <td>1.40</td>\n",
+       "      <td>137.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>209.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>62.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>61.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>38.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>155000.00</td>\n",
+       "      <td>1.10</td>\n",
+       "      <td>143.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>270.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>75.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>582.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>40.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>263358.03</td>\n",
+       "      <td>1.18</td>\n",
+       "      <td>137.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>107.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    age  anaemia  creatinine_phosphokinase  diabetes  ejection_fraction  \\\n",
+       "0  65.0      0.0                      56.0       0.0               25.0   \n",
+       "1  67.0      0.0                     213.0       0.0               38.0   \n",
+       "2  75.0      0.0                     582.0       0.0               20.0   \n",
+       "3  72.0      1.0                     943.0       0.0               25.0   \n",
+       "4  65.0      0.0                     198.0       1.0               35.0   \n",
+       "5  55.0      0.0                    7861.0       0.0               38.0   \n",
+       "6  75.0      1.0                      81.0       0.0               38.0   \n",
+       "7  53.0      1.0                     707.0       0.0               38.0   \n",
+       "8  62.0      0.0                      61.0       1.0               38.0   \n",
+       "9  75.0      0.0                     582.0       0.0               40.0   \n",
+       "\n",
+       "   high_blood_pressure  platelets  serum_creatinine  serum_sodium  sex  \\\n",
+       "0                  0.0  237000.00              5.00         130.0  0.0   \n",
+       "1                  0.0  215000.00              1.20         133.0  0.0   \n",
+       "2                  1.0  265000.00              1.90         130.0  1.0   \n",
+       "3                  1.0  338000.00              1.70         139.0  1.0   \n",
+       "4                  1.0  281000.00              0.90         137.0  1.0   \n",
+       "5                  0.0  263358.03              1.10         136.0  1.0   \n",
+       "6                  1.0  368000.00              4.00         131.0  1.0   \n",
+       "7                  0.0  330000.00              1.40         137.0  1.0   \n",
+       "8                  1.0  155000.00              1.10         143.0  1.0   \n",
+       "9                  0.0  263358.03              1.18         137.0  1.0   \n",
+       "\n",
+       "   smoking   time  DEATH_EVENT  \n",
+       "0      0.0  207.0          0.0  \n",
+       "1      0.0  245.0          0.0  \n",
+       "2      0.0    4.0          1.0  \n",
+       "3      1.0  111.0          1.0  \n",
+       "4      1.0  146.0          0.0  \n",
+       "5      0.0    6.0          1.0  \n",
+       "6      1.0   10.0          1.0  \n",
+       "7      1.0  209.0          0.0  \n",
+       "8      1.0  270.0          0.0  \n",
+       "9      0.0  107.0          0.0  "
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# data inference\n",
+    "df_inf = pd.read_csv('G:\\My Drive\\FTDS\\phase 1\\p1gc3\\h8dsft_p1g3_Ahmad Luay Adnani_inference.csv')\n",
+    "df_inf_copy = df_inf.copy()\n",
+    "df_inf_copy = df_inf.drop(['Unnamed: 0'],axis=1)\n",
+    "df_inf_copy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "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>creatinine_phosphokinase</th>\n",
+       "      <th>ejection_fraction</th>\n",
+       "      <th>platelets</th>\n",
+       "      <th>serum_creatinine</th>\n",
+       "      <th>serum_sodium</th>\n",
+       "      <th>time</th>\n",
+       "      <th>DEATH_EVENT</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>65.0</td>\n",
+       "      <td>56.0</td>\n",
+       "      <td>25.0</td>\n",
+       "      <td>237000.00</td>\n",
+       "      <td>5.00</td>\n",
+       "      <td>130.0</td>\n",
+       "      <td>207.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>67.0</td>\n",
+       "      <td>213.0</td>\n",
+       "      <td>38.0</td>\n",
+       "      <td>215000.00</td>\n",
+       "      <td>1.20</td>\n",
+       "      <td>133.0</td>\n",
+       "      <td>245.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>75.0</td>\n",
+       "      <td>582.0</td>\n",
+       "      <td>20.0</td>\n",
+       "      <td>265000.00</td>\n",
+       "      <td>1.90</td>\n",
+       "      <td>130.0</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>72.0</td>\n",
+       "      <td>943.0</td>\n",
+       "      <td>25.0</td>\n",
+       "      <td>338000.00</td>\n",
+       "      <td>1.70</td>\n",
+       "      <td>139.0</td>\n",
+       "      <td>111.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>65.0</td>\n",
+       "      <td>198.0</td>\n",
+       "      <td>35.0</td>\n",
+       "      <td>281000.00</td>\n",
+       "      <td>0.90</td>\n",
+       "      <td>137.0</td>\n",
+       "      <td>146.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>55.0</td>\n",
+       "      <td>7861.0</td>\n",
+       "      <td>38.0</td>\n",
+       "      <td>263358.03</td>\n",
+       "      <td>1.10</td>\n",
+       "      <td>136.0</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>75.0</td>\n",
+       "      <td>81.0</td>\n",
+       "      <td>38.0</td>\n",
+       "      <td>368000.00</td>\n",
+       "      <td>4.00</td>\n",
+       "      <td>131.0</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>53.0</td>\n",
+       "      <td>707.0</td>\n",
+       "      <td>38.0</td>\n",
+       "      <td>330000.00</td>\n",
+       "      <td>1.40</td>\n",
+       "      <td>137.0</td>\n",
+       "      <td>209.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>62.0</td>\n",
+       "      <td>61.0</td>\n",
+       "      <td>38.0</td>\n",
+       "      <td>155000.00</td>\n",
+       "      <td>1.10</td>\n",
+       "      <td>143.0</td>\n",
+       "      <td>270.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>75.0</td>\n",
+       "      <td>582.0</td>\n",
+       "      <td>40.0</td>\n",
+       "      <td>263358.03</td>\n",
+       "      <td>1.18</td>\n",
+       "      <td>137.0</td>\n",
+       "      <td>107.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    age  creatinine_phosphokinase  ejection_fraction  platelets  \\\n",
+       "0  65.0                      56.0               25.0  237000.00   \n",
+       "1  67.0                     213.0               38.0  215000.00   \n",
+       "2  75.0                     582.0               20.0  265000.00   \n",
+       "3  72.0                     943.0               25.0  338000.00   \n",
+       "4  65.0                     198.0               35.0  281000.00   \n",
+       "5  55.0                    7861.0               38.0  263358.03   \n",
+       "6  75.0                      81.0               38.0  368000.00   \n",
+       "7  53.0                     707.0               38.0  330000.00   \n",
+       "8  62.0                      61.0               38.0  155000.00   \n",
+       "9  75.0                     582.0               40.0  263358.03   \n",
+       "\n",
+       "   serum_creatinine  serum_sodium   time  DEATH_EVENT  \n",
+       "0              5.00         130.0  207.0          0.0  \n",
+       "1              1.20         133.0  245.0          0.0  \n",
+       "2              1.90         130.0    4.0          1.0  \n",
+       "3              1.70         139.0  111.0          1.0  \n",
+       "4              0.90         137.0  146.0          0.0  \n",
+       "5              1.10         136.0    6.0          1.0  \n",
+       "6              4.00         131.0   10.0          1.0  \n",
+       "7              1.40         137.0  209.0          0.0  \n",
+       "8              1.10         143.0  270.0          0.0  \n",
+       "9              1.18         137.0  107.0          0.0  "
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Removing unnecessary features\n",
+    "df_inf_final = df_inf_copy.drop(Drop_Columns,axis=1).sort_index()\n",
+    "df_inf_final"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([1., 0., 1., 1., 0., 1., 1., 0., 0., 0.])"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Predict using RandomForest\n",
+    "\n",
+    "y_pred_inf = rf_gridcv_best.predict(df_inf_final) #rf_gridcv_best from load files\n",
+    "y_pred_inf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "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>DEATH_EVENT_Prediction</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   DEATH_EVENT_Prediction\n",
+       "0                     1.0\n",
+       "1                     0.0\n",
+       "2                     1.0\n",
+       "3                     1.0\n",
+       "4                     0.0\n",
+       "5                     1.0\n",
+       "6                     1.0\n",
+       "7                     0.0\n",
+       "8                     0.0\n",
+       "9                     0.0"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Create DEATH_EVENT Prediction DataFrame\n",
+    "\n",
+    "y_pred_inf_df = pd.DataFrame(y_pred_inf, columns=['DEATH_EVENT_Prediction'],index=df_inf_final.index)\n",
+    "round(y_pred_inf_df.head(10),2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "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>DEATH_EVENT</th>\n",
+       "      <th>DEATH_EVENT_Prediction</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>1.0</td>\n",
+       "      <td>1.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   DEATH_EVENT  DEATH_EVENT_Prediction\n",
+       "0          0.0                     1.0\n",
+       "1          0.0                     0.0\n",
+       "2          1.0                     1.0\n",
+       "3          1.0                     1.0\n",
+       "4          0.0                     0.0\n",
+       "5          1.0                     1.0\n",
+       "6          1.0                     1.0\n",
+       "7          0.0                     0.0\n",
+       "8          0.0                     0.0\n",
+       "9          0.0                     0.0"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Comparing the real default_payment_next_month and predicted classification\n",
+    "model_inf = pd.concat([df_inf_copy['DEATH_EVENT'], y_pred_inf_df['DEATH_EVENT_Prediction']], axis=1).sort_index()\n",
+    "model_inf"
+   ]
+  }
+ ],
+ "metadata": {
+  "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": "3.9.13"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

phase1_ftds_018_rmt.csv

@@ -0,0 +1,300 @@
+age,anaemia,creatinine_phosphokinase,diabetes,ejection_fraction,high_blood_pressure,platelets,serum_creatinine,serum_sodium,sex,smoking,time,DEATH_EVENT
+42.0,1,250,1,15,0,213000.0,1.3,136,0,0,65,1
+46.0,0,168,1,17,1,271000.0,2.1,124,0,0,100,1
+65.0,1,160,1,20,0,327000.0,2.7,116,0,0,8,1
+53.0,1,91,0,20,1,418000.0,1.4,139,0,0,43,1
+50.0,1,582,1,20,1,279000.0,1.0,134,0,0,186,0
+70.0,1,125,0,25,1,237000.0,1.0,140,0,0,15,1
+65.0,1,52,0,25,1,276000.0,1.3,137,0,0,16,0
+70.0,0,161,0,25,0,244000.0,1.2,142,0,0,66,1
+60.0,1,76,1,25,0,196000.0,2.5,132,0,0,77,1
+59.0,1,280,1,25,1,302000.0,1.0,141,0,0,78,1
+60.0,1,156,1,25,1,318000.0,1.2,137,0,0,85,0
+60.0,0,1896,1,25,0,365000.0,2.1,144,0,0,172,1
+65.0,0,56,0,25,0,237000.0,5.0,130,0,0,207,0
+72.0,0,211,0,25,0,274000.0,1.2,134,0,0,207,0
+49.0,1,80,0,30,1,427000.0,1.0,138,0,0,12,0
+65.0,1,128,1,30,1,297000.0,1.6,136,0,0,20,1
+75.0,0,582,1,30,1,263358.03,1.83,134,0,0,23,1
+50.0,1,159,1,30,0,302000.0,1.2,138,0,0,29,0
+50.0,0,124,1,30,1,153000.0,1.2,136,0,1,32,1
+57.0,1,129,0,30,0,395000.0,1.0,140,0,0,42,1
+72.0,1,328,0,30,1,621000.0,1.7,138,0,1,88,1
+60.0,1,582,0,30,1,127000.0,0.9,145,0,0,95,0
+50.0,0,482,1,30,0,329000.0,0.9,132,0,0,109,0
+65.0,0,167,0,30,0,259000.0,0.8,138,0,0,186,0
+48.0,1,131,1,30,1,244000.0,1.6,130,0,0,193,1
+60.0,0,166,0,30,0,62000.0,1.7,127,0,0,207,1
+50.0,0,2522,0,30,1,404000.0,0.5,139,0,0,214,0
+50.0,1,1051,1,30,0,232000.0,0.7,136,0,0,246,0
+50.0,1,249,1,35,1,319000.0,1.0,128,0,0,28,1
+62.0,0,281,1,35,0,221000.0,1.0,136,0,0,108,0
+46.0,1,291,0,35,0,348000.0,0.9,140,0,0,109,0
+65.0,1,335,0,35,1,235000.0,0.8,136,0,0,120,0
+52.0,1,58,0,35,0,277000.0,1.4,136,0,0,120,0
+50.0,1,2334,1,35,0,75000.0,0.9,142,0,0,126,1
+70.0,0,835,0,35,1,305000.0,0.8,133,0,0,145,0
+49.0,0,972,1,35,1,268000.0,0.8,130,0,0,187,0
+55.0,0,582,1,35,1,371000.0,0.7,140,0,0,197,0
+70.0,0,81,1,35,1,533000.0,1.3,139,0,0,212,0
+55.0,0,572,1,35,0,231000.0,0.8,143,0,0,215,0
+70.0,0,88,1,35,1,236000.0,1.2,132,0,0,215,0
+70.0,0,618,0,35,0,327000.0,1.1,142,0,0,245,0
+65.0,0,892,1,35,0,263358.03,1.1,142,0,0,256,0
+60.0,0,235,1,38,0,329000.0,3.0,142,0,0,30,1
+60.0,1,260,1,38,0,255000.0,2.2,132,0,1,45,1
+58.0,0,144,1,38,1,327000.0,0.7,142,0,0,83,0
+86.0,0,582,0,38,0,263358.03,1.83,134,0,0,95,1
+66.0,1,68,1,38,1,162000.0,1.0,136,0,0,95,0
+60.0,0,96,1,38,0,228000.0,0.75,140,0,0,95,0
+80.0,0,776,1,38,1,192000.0,1.3,135,0,0,130,1
+45.0,0,582,1,38,1,263358.03,1.18,137,0,0,185,0
+65.0,0,326,0,38,0,294000.0,1.7,139,0,0,220,0
+45.0,0,582,1,38,0,302000.0,0.9,140,0,0,244,0
+67.0,0,213,0,38,0,215000.0,1.2,133,0,0,245,0
+45.0,0,582,0,38,1,422000.0,0.8,137,0,0,245,0
+55.0,0,84,1,38,0,451000.0,1.3,136,0,0,246,0
+90.0,1,337,0,38,0,390000.0,0.9,144,0,0,256,0
+55.0,0,1820,0,38,0,270000.0,1.2,139,0,0,271,0
+95.0,1,112,0,40,1,196000.0,1.0,138,0,0,24,1
+50.0,0,318,0,40,1,216000.0,2.3,131,0,0,60,1
+70.0,0,69,0,40,0,293000.0,1.7,136,0,0,75,0
+63.0,1,61,1,40,0,221000.0,1.1,140,0,0,86,0
+58.0,1,400,0,40,0,164000.0,1.0,139,0,0,91,0
+46.0,0,719,0,40,1,263358.03,1.18,137,0,0,107,0
+61.0,1,84,0,40,1,229000.0,0.9,141,0,0,110,0
+65.0,0,582,1,40,0,270000.0,1.0,138,0,0,140,0
+60.667,1,151,1,40,1,201000.0,1.0,136,0,0,172,0
+40.0,1,101,0,40,0,226000.0,0.8,141,0,0,187,0
+60.0,1,2281,1,40,0,283000.0,1.0,141,0,0,187,0
+65.0,1,720,1,40,0,257000.0,1.0,136,0,0,210,0
+73.0,1,1185,0,40,1,220000.0,0.9,141,0,0,213,0
+53.0,0,207,1,40,0,223000.0,1.2,130,0,0,214,0
+62.0,1,655,0,40,0,283000.0,0.7,133,0,0,233,0
+51.0,0,582,1,40,0,221000.0,0.9,134,0,0,244,0
+55.0,0,336,0,45,1,324000.0,0.9,140,0,0,74,0
+72.0,0,233,0,45,1,235000.0,2.5,135,0,0,115,1
+40.0,0,244,0,45,1,275000.0,0.9,140,0,0,174,0
+50.0,1,167,1,45,0,362000.0,1.0,136,0,0,187,0
+82.0,1,855,1,50,1,321000.0,1.0,145,0,0,30,1
+70.0,1,69,1,50,1,351000.0,1.0,134,0,0,44,1
+60.0,0,53,0,50,1,286000.0,2.3,143,0,0,87,0
+43.0,1,358,0,50,0,237000.0,1.3,135,0,0,97,0
+49.0,1,69,0,50,0,132000.0,1.0,140,0,0,147,0
+50.0,0,582,0,50,0,153000.0,0.6,134,0,0,172,1
+70.0,0,1202,0,50,1,358000.0,0.9,141,0,0,196,0
+48.0,1,582,1,55,0,87000.0,1.9,121,0,0,15,1
+45.0,0,582,1,55,0,543000.0,1.0,132,0,0,250,0
+45.0,0,615,1,55,0,222000.0,0.8,141,0,0,257,0
+60.0,1,588,1,60,0,194000.0,1.1,142,0,0,33,1
+70.0,0,92,0,60,1,317000.0,0.8,140,0,1,74,0
+42.0,0,582,0,60,0,263358.03,1.18,137,0,0,82,0
+70.0,1,59,0,60,0,255000.0,1.1,136,0,0,85,0
+70.0,1,143,0,60,0,351000.0,1.3,137,0,0,90,1
+60.0,1,96,1,60,1,271000.0,0.7,136,0,0,94,0
+85.0,1,102,0,60,0,507000.0,3.2,138,0,0,94,0
+65.0,1,113,1,60,1,203000.0,0.9,140,0,0,94,0
+58.0,1,200,1,60,0,300000.0,0.8,137,0,0,104,0
+65.0,1,59,1,60,0,172000.0,0.9,137,0,0,107,0
+64.0,1,62,0,60,0,309000.0,1.5,135,0,0,174,0
+75.0,0,675,1,60,0,265000.0,1.4,125,0,0,205,0
+68.0,1,157,1,60,0,208000.0,1.0,140,0,0,237,0
+45.0,0,2060,1,60,0,742000.0,0.8,138,0,0,278,0
+60.0,0,3964,1,62,0,263358.03,6.8,146,0,0,43,1
+65.0,0,157,0,65,0,263358.03,1.5,138,0,0,10,1
+54.0,1,427,0,70,1,151000.0,9.0,137,0,0,196,1
+45.0,0,582,0,80,0,263358.03,1.18,137,0,0,63,0
+45.0,0,582,0,14,0,166000.0,0.8,127,1,0,14,1
+75.0,1,246,0,15,0,127000.0,1.2,137,1,0,10,1
+70.0,0,212,1,17,1,389000.0,1.0,136,1,1,188,0
+75.0,0,582,0,20,1,265000.0,1.9,130,1,0,4,1
+65.0,0,146,0,20,0,162000.0,1.3,129,1,1,7,1
+50.0,1,111,0,20,0,210000.0,1.9,137,1,0,7,1
+70.0,0,582,0,20,1,263358.03,1.83,134,1,1,31,1
+80.0,1,553,0,20,1,140000.0,4.4,133,1,0,41,1
+49.0,0,789,0,20,1,319000.0,1.1,136,1,1,55,1
+72.0,0,364,1,20,1,254000.0,1.3,136,1,1,59,1
+60.0,0,68,0,20,0,119000.0,2.9,127,1,1,64,1
+69.0,0,582,0,20,0,266000.0,1.2,134,1,1,73,1
+60.0,1,47,0,20,0,204000.0,0.7,139,1,1,73,1
+59.0,0,66,1,20,0,70000.0,2.4,134,1,0,135,1
+50.0,1,115,0,20,0,189000.0,0.8,139,1,0,146,0
+45.0,0,582,0,20,1,126000.0,1.6,135,1,0,180,1
+73.0,0,582,0,20,0,263358.03,1.83,134,1,0,198,1
+55.0,0,1199,0,20,0,263358.03,1.83,134,1,1,241,1
+62.0,0,231,0,25,1,253000.0,0.9,140,1,1,10,1
+51.0,0,1380,0,25,1,271000.0,0.9,130,1,0,38,1
+68.0,1,577,0,25,1,166000.0,1.0,138,1,0,43,1
+45.0,0,7702,1,25,1,390000.0,1.0,139,1,0,60,1
+72.0,1,110,0,25,0,274000.0,1.0,140,1,1,65,1
+65.0,0,113,1,25,0,497000.0,1.83,135,1,0,67,1
+57.0,1,115,0,25,1,181000.0,1.1,144,1,0,79,0
+60.0,1,154,0,25,0,210000.0,1.7,135,1,0,82,1
+63.0,1,514,1,25,1,254000.0,1.3,134,1,0,83,0
+65.0,1,305,0,25,0,298000.0,1.1,141,1,0,87,0
+80.0,0,898,0,25,0,149000.0,1.1,144,1,1,87,0
+50.0,0,369,1,25,0,252000.0,1.6,136,1,0,90,0
+68.0,1,646,0,25,0,305000.0,2.1,130,1,0,108,0
+72.0,1,943,0,25,1,338000.0,1.7,139,1,1,111,1
+60.0,1,231,1,25,0,194000.0,1.7,140,1,0,120,0
+50.0,0,250,0,25,0,262000.0,1.0,136,1,1,120,0
+59.0,1,176,1,25,0,221000.0,1.0,136,1,1,150,1
+65.0,0,395,1,25,0,265000.0,1.2,136,1,1,154,1
+58.0,1,145,0,25,0,219000.0,1.2,137,1,1,170,1
+60.0,0,59,0,25,1,212000.0,3.5,136,1,1,187,0
+47.0,0,582,0,25,0,130000.0,0.8,134,1,0,201,0
+58.0,0,582,1,25,0,504000.0,1.0,138,1,0,205,0
+58.0,1,57,0,25,0,189000.0,1.3,132,1,1,205,0
+55.0,0,2017,0,25,0,314000.0,1.1,138,1,0,214,1
+64.0,0,143,0,25,0,246000.0,2.4,135,1,0,214,0
+45.0,1,66,1,25,0,233000.0,0.8,135,1,0,230,0
+65.0,1,258,1,25,0,198000.0,1.4,129,1,0,235,1
+45.0,1,981,0,30,0,136000.0,1.1,137,1,0,11,1
+82.0,0,70,1,30,0,200000.0,1.2,132,1,1,26,1
+60.0,0,2656,1,30,0,305000.0,2.3,137,1,0,30,0
+95.0,1,371,0,30,0,461000.0,2.0,132,1,0,50,1
+42.0,0,5209,0,30,0,226000.0,1.0,140,1,1,87,0
+61.0,0,248,0,30,1,267000.0,0.7,136,1,1,104,0
+50.0,0,1548,0,30,1,211000.0,0.8,138,1,0,108,0
+50.0,0,185,0,30,0,266000.0,0.7,141,1,1,112,0
+52.0,0,132,0,30,0,218000.0,0.7,136,1,1,112,0
+75.0,1,582,0,30,0,225000.0,1.83,134,1,0,113,1
+45.0,0,2442,1,30,0,334000.0,1.1,139,1,0,129,1
+40.0,0,478,1,30,0,303000.0,0.9,136,1,0,148,0
+60.667,1,104,1,30,0,389000.0,1.5,136,1,0,171,1
+73.0,1,231,1,30,0,160000.0,1.18,142,1,1,180,0
+70.0,0,232,0,30,0,173000.0,1.2,132,1,0,210,0
+65.0,0,582,1,30,0,249000.0,1.3,136,1,1,212,0
+52.0,1,191,1,30,1,334000.0,1.0,142,1,1,216,0
+44.0,0,582,1,30,1,263358.03,1.6,130,1,1,244,0
+60.0,1,257,1,30,0,150000.0,1.0,137,1,1,245,0
+42.0,0,64,0,30,0,215000.0,3.8,128,1,1,250,0
+80.0,1,123,0,35,1,388000.0,9.4,133,1,1,10,1
+68.0,1,220,0,35,1,289000.0,0.9,140,1,1,20,1
+69.0,0,582,1,35,0,228000.0,3.5,134,1,0,30,1
+70.0,1,75,0,35,0,223000.0,2.7,138,1,1,54,0
+55.0,0,109,0,35,0,254000.0,1.1,139,1,1,60,0
+45.0,0,582,0,35,0,385000.0,1.0,145,1,0,61,1
+58.0,0,582,1,35,0,122000.0,0.9,139,1,1,71,0
+85.0,0,5882,0,35,0,243000.0,1.0,132,1,1,72,1
+55.0,0,47,0,35,1,173000.0,1.1,137,1,0,79,0
+45.0,1,1876,1,35,0,226000.0,0.9,138,1,0,88,0
+45.0,0,292,1,35,0,850000.0,1.3,142,1,1,88,0
+55.0,0,60,0,35,0,228000.0,1.2,135,1,1,90,0
+53.0,1,270,1,35,0,227000.0,3.4,145,1,0,105,0
+81.0,0,4540,0,35,0,231000.0,1.18,137,1,1,107,0
+60.0,0,2261,0,35,1,228000.0,0.9,136,1,0,115,0
+50.0,0,1846,1,35,0,263358.03,1.18,137,1,1,119,0
+45.0,1,130,0,35,0,174000.0,0.8,139,1,1,121,0
+51.0,1,582,1,35,0,263358.03,1.5,136,1,1,145,0
+65.0,0,198,1,35,1,281000.0,0.9,137,1,1,146,0
+80.0,0,582,1,35,0,350000.0,2.1,134,1,0,174,0
+60.0,0,1211,1,35,0,263358.03,1.8,113,1,1,186,0
+65.0,1,135,0,35,1,290000.0,0.8,134,1,0,194,0
+73.0,0,582,0,35,1,203000.0,1.3,134,1,0,195,0
+68.0,1,1021,1,35,0,271000.0,1.1,134,1,0,197,0
+42.0,1,86,0,35,0,365000.0,1.1,139,1,1,201,0
+55.0,1,2794,0,35,1,141000.0,1.0,140,1,0,206,0
+70.0,0,93,0,35,0,185000.0,1.1,134,1,1,208,0
+40.0,1,129,0,35,0,255000.0,0.9,137,1,0,209,0
+40.0,0,90,0,35,0,255000.0,1.1,136,1,1,212,0
+40.0,0,624,0,35,0,301000.0,1.0,142,1,1,214,0
+50.0,1,298,0,35,0,362000.0,0.9,140,1,1,240,0
+40.0,0,582,1,35,0,222000.0,1.0,132,1,0,244,0
+60.0,0,253,0,35,0,279000.0,1.7,140,1,0,250,0
+60.0,0,320,0,35,0,133000.0,1.4,139,1,0,258,0
+63.0,1,103,1,35,0,179000.0,0.9,136,1,1,270,0
+55.0,0,7861,0,38,0,263358.03,1.1,136,1,0,6,1
+75.0,1,81,0,38,1,368000.0,4.0,131,1,1,10,1
+50.0,1,168,0,38,1,276000.0,1.1,137,1,0,11,1
+87.0,1,149,0,38,0,262000.0,0.9,140,1,0,14,1
+80.0,0,148,1,38,0,149000.0,1.9,144,1,1,23,1
+58.0,1,60,0,38,0,153000.0,5.8,134,1,0,26,1
+94.0,0,582,1,38,1,263358.03,1.83,134,1,0,27,1
+50.0,0,582,1,38,0,310000.0,1.9,135,1,1,35,1
+60.0,0,582,1,38,1,451000.0,0.6,138,1,1,40,1
+75.0,1,203,1,38,1,283000.0,0.6,131,1,1,74,0
+63.0,0,936,0,38,0,304000.0,1.1,133,1,1,88,0
+80.0,0,805,0,38,0,263358.03,1.1,134,1,0,109,1
+75.0,0,99,0,38,1,224000.0,2.5,134,1,0,162,1
+85.0,0,212,0,38,0,186000.0,0.9,136,1,0,187,0
+53.0,1,707,0,38,0,330000.0,1.4,137,1,1,209,0
+54.0,0,582,1,38,0,264000.0,1.8,134,1,0,213,0
+61.0,1,80,1,38,0,282000.0,1.4,137,1,0,213,0
+58.0,0,132,1,38,1,253000.0,1.0,139,1,0,230,0
+61.0,0,582,1,38,0,147000.0,1.2,141,1,0,237,0
+56.0,1,135,1,38,0,133000.0,1.7,140,1,0,244,0
+70.0,0,582,1,38,0,25100.0,1.1,140,1,0,246,0
+65.0,0,1688,0,38,0,263358.03,1.1,138,1,1,250,0
+52.0,0,190,1,38,0,382000.0,1.0,140,1,1,258,0
+62.0,0,61,1,38,1,155000.0,1.1,143,1,1,270,0
+45.0,0,2413,0,38,0,140000.0,1.4,140,1,1,280,0
+90.0,1,47,0,40,1,204000.0,2.1,132,1,1,8,1
+60.0,1,607,0,40,0,216000.0,0.6,138,1,1,54,0
+41.0,0,148,0,40,0,374000.0,0.8,140,1,1,68,0
+42.0,0,102,1,40,0,237000.0,1.2,140,1,0,74,0
+44.0,0,84,1,40,1,235000.0,0.7,139,1,0,79,0
+60.0,1,754,1,40,1,328000.0,1.2,126,1,0,91,0
+60.0,0,582,0,40,0,217000.0,3.7,134,1,0,96,1
+75.0,0,582,0,40,0,263358.03,1.18,137,1,0,107,0
+66.0,1,72,0,40,1,242000.0,1.2,134,1,0,121,0
+63.0,1,582,0,40,0,448000.0,0.9,137,1,1,123,0
+52.0,0,3966,0,40,0,325000.0,0.9,140,1,1,146,0
+69.0,0,1419,0,40,0,105000.0,1.0,135,1,1,147,0
+55.0,0,835,0,40,0,279000.0,0.7,140,1,1,147,0
+50.0,1,121,1,40,0,260000.0,0.7,130,1,0,175,0
+78.0,1,64,0,40,0,277000.0,0.7,137,1,1,187,0
+55.0,0,66,0,40,0,203000.0,1.0,138,1,0,233,0
+42.0,0,64,0,40,0,189000.0,0.7,140,1,0,245,0
+70.0,0,2695,1,40,0,241000.0,1.0,137,1,0,247,0
+70.0,0,582,0,40,0,51000.0,2.7,136,1,1,250,0
+50.0,1,54,0,40,0,279000.0,0.8,141,1,0,250,0
+55.0,1,170,1,40,0,336000.0,1.2,135,1,0,250,0
+70.0,0,122,1,45,1,284000.0,1.3,136,1,1,26,1
+85.0,0,23,0,45,0,360000.0,3.0,132,1,0,28,1
+70.0,0,571,1,45,1,185000.0,1.2,139,1,1,33,1
+70.0,0,66,1,45,0,249000.0,0.8,136,1,1,80,0
+60.0,0,897,1,45,0,297000.0,1.0,133,1,0,80,0
+75.0,0,582,0,45,1,263358.03,1.18,137,1,0,87,0
+55.0,0,748,0,45,0,263000.0,1.3,137,1,0,88,0
+60.0,1,1082,1,45,0,250000.0,6.1,131,1,0,107,0
+50.0,0,115,0,45,1,184000.0,0.9,134,1,1,118,0
+59.0,1,129,0,45,1,362000.0,1.1,139,1,1,121,0
+77.0,1,418,0,45,0,223000.0,1.8,145,1,0,180,1
+63.0,1,1767,0,45,0,73000.0,0.7,137,1,0,186,0
+53.0,1,582,0,45,0,305000.0,1.1,137,1,1,209,0
+55.0,1,180,0,45,0,263358.03,1.18,137,1,1,211,0
+50.0,0,245,0,45,1,274000.0,1.0,133,1,0,215,0
+50.0,0,196,0,45,0,395000.0,1.6,136,1,1,285,0
+82.0,1,379,0,50,0,47000.0,1.3,136,1,0,13,1
+65.0,0,94,1,50,1,188000.0,1.0,140,1,0,29,1
+90.0,1,60,1,50,0,226000.0,1.0,134,1,0,30,1
+72.0,0,127,1,50,1,218000.0,1.0,134,1,0,33,0
+65.0,0,224,1,50,0,149000.0,1.3,137,1,1,72,0
+67.0,0,582,0,50,0,263358.03,1.18,137,1,1,76,0
+79.0,1,55,0,50,1,172000.0,1.8,133,1,0,78,0
+51.0,0,78,0,50,0,406000.0,0.7,140,1,0,79,0
+85.0,1,910,0,50,0,235000.0,1.3,134,1,0,121,0
+78.0,0,224,0,50,0,481000.0,1.4,138,1,1,192,0
+65.0,0,118,0,50,0,194000.0,1.1,145,1,1,200,0
+77.0,1,109,0,50,1,406000.0,1.1,137,1,0,209,0
+75.0,0,119,0,50,1,248000.0,1.1,148,1,0,209,0
+53.0,0,56,0,50,0,308000.0,0.7,135,1,1,231,0
+60.0,1,315,1,60,0,454000.0,1.1,131,1,1,10,1
+53.0,0,63,1,60,0,368000.0,0.8,135,1,0,22,0
+65.0,1,68,1,60,1,304000.0,0.8,140,1,0,79,0
+58.0,1,133,0,60,1,219000.0,1.0,141,1,0,83,0
+85.0,0,129,0,60,0,306000.0,1.2,132,1,1,90,1
+60.0,1,737,0,60,1,210000.0,1.5,135,1,1,95,0
+53.0,1,1808,0,60,1,249000.0,0.7,138,1,1,106,0
+63.0,0,193,0,60,1,295000.0,1.3,145,1,1,107,0
+64.0,0,1610,0,60,0,242000.0,1.0,137,1,0,113,0
+62.0,0,30,1,60,1,244000.0,0.9,139,1,0,117,0
+53.0,0,196,0,60,0,220000.0,0.7,133,1,1,134,0
+70.0,1,171,0,60,1,176000.0,1.1,145,1,1,146,0
+60.0,1,95,0,60,0,337000.0,1.0,138,1,1,146,0
+63.0,1,122,1,60,0,267000.0,1.2,145,1,0,147,0
+45.0,0,308,1,60,1,377000.0,1.0,136,1,0,186,0
+70.0,0,97,0,60,1,220000.0,0.9,138,1,0,186,0
+53.0,1,446,0,60,1,263358.03,1.0,139,1,0,215,0
+50.0,0,582,0,62,1,147000.0,0.8,140,1,1,192,0

prediction.py

@@ -0,0 +1,64 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import pickle
+import json
+# Load All Files
+
+with open('rf_gridcv_best.pkl', 'rb') as file_1:
+  rf_gridcv_best = pickle.load(file_1)
+
+with open('Drop_Columns.txt', 'r') as file_2:
+  Drop_Columns = json.load(file_2)
+
+def run():
+  with st.form(key='form_fifa_2022'):
+      age = st.number_input('age',min_value=0,max_value=99,value=55,step=1,help='Age of Patients')
+      anemia = st.number_input('Have Anemia ? ',min_value=0, max_value=1,value=0,help='0 for No, 1 for Yes')
+      creatinine_phosphokinase = st.number_input('Level of the CPK enzyme in the blood',min_value=0,max_value=9999,value=600)
+      diabetes = st.number_input('Have Diabetes?',min_value=0,max_value=1000000000,value=0,help='0 for No, 1 for Yes')
+      ejection_fraction = st.number_input('Percentage of blood leaving the heart at each contraction (%)',min_value=0,max_value=100,value=38)
+      high_blood_pressure = st.number_input('Have Diabetes?',min_value=0,max_value=1,value=0,help='0 for No, 1 for Yes')
+      platelets = st.number_input('Platelets in the blood (kiloplatelets/mL)',min_value=0,max_value=999999,value=0,help='in kiloplatelets/mL')
+      serum_creatinine = st.number_input('Level of serum creatinine in the blood ',min_value=0,max_value=10,value=0,help='in mg/dL')
+      serum_sodium = st.number_input('Level of serum sodium in the blood',min_value=0,max_value=150,value=0,help='in mEq/dL')
+      sex = st.number_input('Gender',min_value=0,max_value=1,value=0,help='(Female = 0, Male = 1)')
+      smoking = st.number_input('Smoker or Not Smoker ?',min_value=0,max_value=1,value=0,help='(No= 0, Yes = 1)')
+      time = st.number_input('Follow Up Period',min_value=0,max_value=285,value=0,help='in Days')
+
+      
+     
+      submitted = st.form_submit_button(' Still Alive or Not ?')
+
+  df_inf = {
+      'age': age,
+      'anaemia': anemia,
+      'creatinine_phosphokinase': creatinine_phosphokinase,
+      'diabetes': diabetes,
+      'ejection_fraction': ejection_fraction,
+      'high_blood_pressure': high_blood_pressure,
+      'platelets': platelets,
+      'serum_creatinine': serum_creatinine,
+      'serum_sodium': serum_sodium,
+      'sex': sex,
+      'smoking': smoking,
+      'time':time
+  }
+  df_inf = pd.DataFrame([df_inf])
+  # Data Inference
+  df_inf_copy = df_inf.copy()
+  df_inf_copy
+
+  # Removing unnecessary features
+  df_inf_final = df_inf_copy.drop(Drop_Columns,axis=1).sort_index()
+  df_inf_final
+  
+  st.dataframe(df_inf_final)
+
+  if submitted:
+      # Predict using RandomForest
+      y_pred_inf = rf_gridcv_best.predict(df_inf_final)
+      st.write('# Still Alive or Not ? (0 = Alive, 1 = Deceased) ',str(int(y_pred_inf)))
+
+if __name__ == '__main__':
+    run()

requirements.txt

@@ -0,0 +1,8 @@
+streamlit
+pandas
+seaborn
+matplotlib
+numpy
+scikit-learn==1.2.1
+imbalanced-learn==0.10.1
+plotly

rf_gridcv_best.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da094101619cb3174b40fff2ac748a76514cedbc731035ea8d9330f29e2e6a22
+size 67133