Spaces:
Runtime error
Runtime error
#!/usr/bin/env python | |
# coding: utf-8 | |
# ## Data Loading | |
# Importing the necessary libraries, like pandas, numpy and some plotting libraries such as matplotlib and seaborn | |
# In[ ]: | |
import pandas as pd | |
import numpy as np | |
import matplotlib | |
import matplotlib.pyplot as plt | |
import seaborn as sns | |
get_ipython().run_line_magic('matplotlib', 'inline') | |
# Set the default font size, figure size and the grid in the plot | |
# In[ ]: | |
sns.set_style('darkgrid') | |
matplotlib.rcParams['font.size'] = 14 | |
matplotlib.rcParams['figure.figsize'] = (10, 6) | |
matplotlib.rcParams['figure.facecolor'] = '#00000000' | |
# Reading of data as a pandas dataframe and named as **df** | |
# In[ ]: | |
df = pd.read_csv('Walmart.csv') | |
# In[ ]: | |
df | |
# **About Data:** | |
# * Store - the store number | |
# * Date - the week of sales | |
# * Weekly_Sales - sales for the given store | |
# * Holiday_Flag - whether the week is a special holiday week 1 β Holiday week 0 β Non-holiday week | |
# * Temperature - Temperature on the day of sale | |
# * Fuel_Price - Cost of fuel in the region | |
# * CPI β Prevailing consumer price index | |
# * Unemployment - Prevailing unemployment rate | |
# **Insights:** | |
# | |
# * Here the target columns is Weekly_Sales. | |
# * The data is related to walmart store of united state of america. Where **Store**, **Holiday_Flag** are categorical in nature | |
# * The data is collected over a 45 stores and weekly sales gives the sales of the crossponding store. | |
# | |
# ## Data Exploration and Modification | |
# In[ ]: | |
df.info() # it gives the information (like count and data type) of the dataset | |
# Here Date columns is **object** and other remain columns are **interger or float** in nature. Now using the pandas I change the date column datatype(i.e. object) into a pandas-datetime. | |
# In[ ]: | |
df.Date=pd.to_datetime(df.Date) | |
# Using the date column i create three seperate columns of weekday, month and year and added to the existing dataset. | |
# In[ ]: | |
df['weekday'] = df.Date.dt.weekday | |
df['month'] = df.Date.dt.month | |
df['year'] = df.Date.dt.year | |
# Now I drop the date columns because of no use of it. | |
# In[ ]: | |
df.drop(['Date'], axis=1, inplace=True) | |
# Hence the modified dataset is look like: | |
# In[ ]: | |
df.head(3) | |
# Explored the unique values of the weekday, month and year columns as follows: | |
# In[ ]: | |
print('years unique value', df.year.unique()) | |
print('months unique value', df.month.unique()) | |
print('weekday unique value', df.weekday.unique()) | |
# Months and weekday are as usual, but the data is taken from year 2010, 2011, 2012 only. | |
# Now to get the idea of distribution of the dataset, I used describe function which gives a table of various statistical values of all the columns | |
# In[ ]: | |
df.describe() | |
# **Insights:** | |
# * Temperature - has values ranges from (-2, 100.1) Fahrenhite. | |
# * CPI - is ranges from 126 to 227 with a standard deviation of 39.35 | |
# * Unemployment - is ranges from 3.87 to 14.31 with a standard deviation of 1.87 | |
# In[ ]: | |
original_df = df.copy() # made the copy of dataframe to check the dublicates values in the dataset | |
# Checking of dublicates values : | |
# In[ ]: | |
counter = 0 | |
rs,cs = original_df.shape | |
df.drop_duplicates(inplace=True) | |
if df.shape==(rs,cs): | |
print('The dataset doesn\'t have any duplicates') | |
else: | |
print('Number of duplicates dropped/fixed ---> {rs-df.shape[0]}') | |
# Checking of missing values : | |
# In[ ]: | |
df.isnull().sum() | |
# Dataset doesn't have null values | |
# ## Data Visualization | |
# In[ ]: | |
df.head(3) | |
# Here we have: | |
# | |
# **Numerical columns:** Weekly_sales, temperature, fuel_price, cpi, unemployment | |
# | |
# **Categorical columns:** Holiday_flag, Weekday, month, year | |
# | |
# Now plotted the count plot to get the distribution or frequency of the columns | |
# In[ ]: | |
fig, axes = plt.subplots(2, 2, figsize=(16, 8)) | |
#axes[0,0].set_title('Holiday Count plot') | |
sns.countplot(x='Holiday_Flag', data=df, ax= axes[0,0]) | |
#axes[0,1].set_title('Weekday Count plot') | |
sns.countplot(x='weekday', data=df, ax= axes[0,1]); | |
#axes[1,0].set_title('month Count plot') | |
sns.countplot(x='month', data=df, ax= axes[1,0]); | |
#axes[1,1].set_title('year Count plot') | |
sns.countplot(x='year', data=df, ax= axes[1,1]); | |
# **Insights:** | |
# | |
# * In Holiday flag most of the time there is no holiday in that week. | |
# * In weekdays columns observations are mostly related to the day 4 | |
# * Most of the observation in the data is from the month of april | |
# * Most of the observation in the data is from year 2011 | |
# To get the idea of how many observations are there in dataset crossponding to each store, I again plot a count plot. | |
# In[ ]: | |
plt.figure(figsize= (18,8)) | |
sns.countplot(x= 'Store', data= df); | |
plt.show() | |
# All the store have equal number of data in the set | |
# In[ ]: | |
df.head(1) | |
# To analyze the distribution of the data, I plotted the histogram and boxplot for Temperature, Unemployment, Fuel_Price, CPI. | |
# In[ ]: | |
fig, axes = plt.subplots(4, 2, figsize=(16, 16)) | |
# axes[0,0].set_title('Temperature') | |
sns.histplot(x= 'Temperature', data= df, ax= axes[0,0]) | |
sns.boxplot(x= 'Temperature', data= df, ax= axes[0,1]) | |
# axes[1,0].set_title('Unemployment') | |
sns.histplot(x= 'Unemployment', data= df, ax= axes[1,0]) | |
sns.boxplot(x= 'Unemployment', data= df, ax= axes[1,1]) | |
# axes[2,0].set_title('Fuel_Price') | |
sns.histplot(x= 'Fuel_Price', data= df, ax= axes[2,0]) | |
sns.boxplot(x = 'Fuel_Price', data= df, ax= axes[2,1]) | |
# axes[3,0].set_title('CPI') | |
sns.histplot(x= 'CPI', data= df, ax= axes[3,0]) | |
sns.boxplot(x= 'CPI', data= df, ax= axes[3,1]); | |
# **Insights:** | |
# | |
# * Temperature: Crossponding to the lower temperature, there is a presence of outlier. | |
# * Umemployment: The outlier is present in the dataset crossponding to higher and lower both values. | |
# * CPI: It is either very low or very high. | |
# In[ ]: | |
# Removing the outlier from Temperature column | |
Q1 = df['Temperature'].quantile(0.25) | |
Q3 = df['Temperature'].quantile(0.75) | |
IQR = Q3 - Q1 | |
df = df[df['Temperature'] <= (Q3+(1.5*IQR))] | |
df = df[df['Temperature'] >= (Q1-(1.5*IQR))] | |
# In[ ]: | |
# Removing the outlier from Unemployment column | |
Q1 = df['Unemployment'].quantile(0.25) | |
Q3 = df['Unemployment'].quantile(0.75) | |
IQR = Q3 - Q1 | |
df = df[df['Unemployment'] <= (Q3+(1.5*IQR))] | |
df = df[df['Unemployment'] >= (Q1-(1.5*IQR))] | |
# In[ ]: | |
df.shape | |
# On the process of removing outlier, **484 data** points are removed from data-set | |
# ## Encoding | |
# Encoding is a process to convert the categorical columns into a numerical columns, as it is not a good preactice to train a model with categorical inputs. | |
# In[ ]: | |
cat_cols = ['Store', 'Holiday_Flag', 'weekday', 'month', 'year'] # these are the categorical columns | |
# In[ ]: | |
df[cat_cols].nunique() # Counting the unique value in each of the categorical columns. | |
# In[ ]: | |
# Imported OneHotEncoder to perfrom the encoding | |
from sklearn.preprocessing import OneHotEncoder | |
# Creating a object of the encoder function | |
encoder = OneHotEncoder(sparse=False, handle_unknown='ignore') | |
# Fit the encoder object to the dataset which i want to convert into numerical form. | |
encoder.fit(df[cat_cols]) | |
# In[ ]: | |
# Creating a list of the encoded columns | |
encoded_cols = list(encoder.get_feature_names(cat_cols)) | |
print(encoded_cols) | |
# In[ ]: | |
# Now i added those encoded columns into the original dataset by transforming it into a categorical form. | |
df[encoded_cols] = encoder.transform(df[cat_cols]) | |
# In[ ]: | |
df.shape | |
# ## Standardization | |
# To scale all the column values to specific range of 0 - 1, I used standard scaler function. It is important to give the equal weights to all the columns. | |
# In[ ]: | |
# Importing a MinMaxScaler | |
from sklearn.preprocessing import MinMaxScaler | |
# Creating Scaler Object | |
scaler = MinMaxScaler() | |
# Fitted the scaler to the dataset | |
scaler.fit(df) | |
# Transformed the dataset using the fitted scaler object | |
scaled_df = scaler.transform(df) | |
# In[ ]: | |
# Converting the output scaled dataframe into a pandas dataframe | |
scaled_df = pd.DataFrame(data = scaled_df, columns = df.columns) | |
# In[ ]: | |
# Checking the output dataframe | |
scaled_df.head(3) | |
# ## Train-Test-Split | |
# Split the dataset into the two part: | |
# 1. Training dataset (used to train the model) | |
# 2. Testing dataset (used to test the model) | |
# In[ ]: | |
# Drop the sales columns to get the input features | |
X = scaled_df.drop('Weekly_Sales', axis=1) | |
# Use the sales column as a target columns | |
y = scaled_df['Weekly_Sales'] | |
# In[ ]: | |
# Importing train test split | |
from sklearn.model_selection import train_test_split | |
# dividing the dataset into the train and the test parts and each part has input feature and target features | |
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state = 42) | |
# In[ ]: | |
# Printin the shape of all the dataset | |
X_train.shape, X_test.shape, y_train.shape, y_test.shape | |
# ## Feature Selection | |
# Out of all the 78 features all are not important and we have to choose the important feature out of all the features | |
# In[ ]: | |
# import a linear regerssion model | |
from sklearn.linear_model import LinearRegression | |
# import a Random Forest Regressor model | |
from sklearn.ensemble import RandomForestRegressor | |
# import a mean squared error for model evaluation | |
from sklearn.metrics import mean_squared_error | |
# import a r2 score for model evaluation | |
from sklearn.metrics import r2_score | |
# import a RFE model for feature selection | |
from sklearn.feature_selection import RFE | |
# In[ ]: | |
# Creatint a list to store training and test error | |
Trr=[]; Tss=[]; n=3 | |
order=['ord-'+str(i) for i in range(2,n)] | |
Trd = pd.DataFrame(np.zeros((10,n-2)), columns=order) | |
Tsd = pd.DataFrame(np.zeros((10,n-2)), columns=order) | |
m=df.shape[1]-2 | |
for i in range(m): | |
# creating a linear regression model object | |
lm = LinearRegression() | |
# creating a rfe model object with linear regression model and with a parameter of the number of features | |
rfe = RFE(lm, n_features_to_select=X_train.shape[1]-i) | |
# fitting the rfe model to the trainig dataset | |
rfe = rfe.fit(X_train, y_train) | |
# creating a linear regression model object for prediction | |
LR = LinearRegression() | |
# fitted the lr model using the selected features | |
LR.fit(X_train.loc[:,rfe.support_], y_train) | |
# Made the prediction using the linear regression model | |
pred1 = LR.predict(X_train.loc[:,rfe.support_]) # make the prediction on the trainig dataset | |
pred2 = LR.predict(X_test.loc[:,rfe.support_]) # make the prediction on the test dataset | |
# Insert the mse into the Trr and Tss for train and test respectively | |
Trr.append(np.sqrt(mean_squared_error(y_train, pred1))) | |
Tss.append(np.sqrt(mean_squared_error(y_test, pred2))) | |
# In[ ]: | |
plt.plot(Trr, label= 'Train RMSE') | |
plt.plot(Tss, label= 'Test RMSE') | |
plt.legend() | |
plt.show() | |
# If we Recursively Eleminate at most **Ten** features then the score is maximum. | |
# In[2]: | |
# Eleminating 10 features and using Linear Regresion model the error printed as follows which is the best possible score. | |
# creating a linear regression model object | |
lm = LinearRegression() | |
# creating a rfe model object with linear regression model and with number of features equal to 10. | |
rfe = RFE(lm,n_features_to_select=X_train.shape[1]-9) | |
# fitting the rfe model to the trainig dataset | |
rfe = rfe.fit(X_train, y_train) | |
# creating a linear regression model object for prediction | |
LR = LinearRegression() | |
# fitted the lr model using the selected features | |
LR.fit(X_train.loc[:,rfe.support_], y_train) | |
# Made the prediction using the linear regression model | |
pred1 = LR.predict(X_train.loc[:,rfe.support_]) | |
pred2 = LR.predict(X_test.loc[:,rfe.support_]) | |
# Printing the results as a MSE and r2_score. | |
print("MSE train",np.sqrt(mean_squared_error(y_train, pred1))) | |
print("MSE test",np.sqrt(mean_squared_error(y_test, pred2))) | |
print("r2_score train - {}".format(r2_score(y_train, pred1))) | |
print("r2_score test - {}".format(r2_score(y_test, pred2))) | |
# Now Removing the 10 features and create the New training and test dataset | |
# In[ ]: | |
X_train = X_train.loc[:,rfe.support_] | |
X_test = X_test.loc[:,rfe.support_] | |
# Now onwards I am going to use various models | |
# ## Linear Regression | |
# In[ ]: | |
lr =LinearRegression() | |
lr.fit(X_train, y_train) | |
pred1 = lr.predict(X_train) | |
pred2 = lr.predict(X_test) | |
print("Root Mean Squared Error train {}".format(np.mean(mean_squared_error(y_train, pred1)))) | |
print("Root Mean Squared Error test {}".format(np.sqrt(mean_squared_error(y_test, pred2)))) | |
print("r2_score train {}".format(r2_score(y_train, pred1))) | |
print("r2_score test {}".format(r2_score(y_test, pred2))) | |
# **Ridge Regression** | |
# In[ ]: | |
from sklearn.linear_model import Ridge | |
rr = Ridge() | |
rr.fit(X_train, y_train) | |
predrr1 = rr.predict(X_train) | |
predrr2 = rr.predict(X_test) | |
print("Root Mean Squared Error train {}".format(np.mean(mean_squared_error(y_train, predrr1)))) | |
print("Root Mean Squared Error test {}".format(np.sqrt(mean_squared_error(y_test, predrr2)))) | |
print("r2_score train {}".format(r2_score(y_train, predrr1))) | |
print("r2_score test {}".format(r2_score(y_test, predrr2))) | |
# **Lasso Regression** | |
# In[ ]: | |
from sklearn.linear_model import Lasso | |
lr = Lasso() | |
lr.fit(X_train, y_train) | |
predlr1 = lr.predict(X_train) | |
predlr2 = lr.predict(X_test) | |
print("Root Mean Squared Error train {}".format(np.mean(mean_squared_error(y_train, predlr1)))) | |
print("Root Mean Squared Error test {}".format(np.sqrt(mean_squared_error(y_test, predlr2)))) | |
print("r2_score train {}".format(r2_score(y_train, predlr1))) | |
print("r2_score test {}".format(r2_score(y_test, predlr2))) | |
# **ElasticNet Regression** | |
# In[ ]: | |
from sklearn.linear_model import ElasticNet | |
en = ElasticNet() | |
en.fit(X_train, y_train) | |
predlr1 = en.predict(X_train) | |
predlr2 = en.predict(X_test) | |
print("Root Mean Squared Error train {}".format(np.mean(mean_squared_error(y_train, predlr1)))) | |
print("Root Mean Squared Error test {}".format(np.sqrt(mean_squared_error(y_test, predlr2)))) | |
print("r2_score train {}".format(r2_score(y_train, predlr1))) | |
print("r2_score test {}".format(r2_score(y_test, predlr2))) | |
# **Polynomial Regression** | |
# In[ ]: | |
from sklearn.preprocessing import PolynomialFeatures | |
# In[ ]: | |
Trr = [] | |
Tss = [] | |
for i in range(2,4): | |
poly_reg = PolynomialFeatures(degree = i) | |
pl_X_train = poly_reg.fit_transform(X_train) | |
pl_X_test = poly_reg.fit_transform(X_test) | |
lr = LinearRegression() | |
lr.fit(pl_X_train, y_train) | |
pred_poly_train = lr.predict(pl_X_train) | |
Trr.append(np.sqrt(mean_squared_error(y_train, pred_poly_train))) | |
pred_poly_test = lr.predict(pl_X_test) | |
Tss.append(np.sqrt(mean_squared_error(y_test, pred_poly_test))) | |
# In[ ]: | |
plt.figure(figsize=[15,6]) | |
plt.subplot(1,2,1) | |
plt.plot(range(2,4), Trr, label= 'Training') | |
plt.plot(range(2,4), Tss, label= 'Testing') | |
plt.title('Polynomial Feature on training data') | |
plt.xlabel('Degree') | |
plt.ylabel('RMSE') | |
plt.legend() | |
# It is clear that in between 2-4 degree polynomial regression 2 has Bais-variance tradeoff | |
# In[ ]: | |
poly_reg = PolynomialFeatures(degree = 2) | |
pl_X_train = poly_reg.fit_transform(X_train) | |
pl_X_test = poly_reg.fit_transform(X_test) | |
lr = LinearRegression() | |
lr.fit(pl_X_train, y_train) | |
pred_poly_train = lr.predict(pl_X_train) | |
print("r2_score train {}".format(r2_score(pred_poly_train, y_train))) | |
pred_poly_test = lr.predict(pl_X_test) | |
print("r2_score test {}".format(r2_score(pred_poly_test, y_test))) | |
print("Root Mean Squared Error train {}".format(np.mean(mean_squared_error(y_train, pred_poly_train)))) | |
print("Root Mean Squared Error test {}".format(np.sqrt(mean_squared_error(y_test, pred_poly_test)))) | |
# In[ ]: | |
#creating a tabel | |
tabel = { | |
'Train R2': [0.9324387485162124, 0.9323641360074176, 0.0, 0.0, 0.9563932198334125], | |
'Test R2' : [0.9223162582948724, 0.9219331606995953, -0.00014816618161050954, -0.00014816618161050954, -0.0005599911350040454], | |
'Train RMSE' : [0.0016695395619648289, 0.0016713833486400986, 0.024711495499242828, 0.024711495499242828, 0.0010346077251656776 ], | |
'Test RMSE' : [0.04569350618906344, 0.04580603645234492, 0.16395383804559885, 0.16395383804559885, 730742413.004261 ] | |
} | |
# In[ ]: | |
df_new = pd.DataFrame(tabel) | |
# In[ ]: | |
df_new.index = ['Linear Regression', 'Ridge Regression', 'Lasso Regression', 'ElasticNet Regression', 'Polynomial Regression'] | |
# In[ ]: | |
df_new | |
# It is clear that Linear Regression is the Best Model in the dataset, with test accuracy of 92%(approx). | |
# | |
# To improve the accuracy further we can apply other regressor i.e. Random Forest, G | |
# Now I am going to imporve the accuracy till 98% - 99%. For this I have to use Decision Tree or Random Forest etc. | |
# **Decision Tree Regressor** | |
# In[ ]: | |
from sklearn.tree import DecisionTreeRegressor | |
dt = DecisionTreeRegressor() | |
dt.fit(X_train, y_train) | |
# In[ ]: | |
pred_dt1 = dt.predict(X_train) | |
pred_dt2 = dt.predict(X_test) | |
print("RMSE for train {}".format(np.sqrt(mean_squared_error(y_train, pred_dt1)))) | |
print("RMSE for test {}".format(np.sqrt(mean_squared_error(y_test, pred_dt2)))) | |
print('Accuracy Score train: ', dt.score(X_train, y_train)) | |
print('Accuracy Score test: ', dt.score(X_test, y_test)) | |
# In[ ]: | |
max_depth_range = np.arange(1,40,1) | |
for x in max_depth_range: | |
dt = DecisionTreeRegressor(max_depth= x) | |
dt.fit(X_train, y_train) | |
pred_dt1 = dt.predict(X_train) | |
pred_dt2 = dt.predict(X_test) | |
print('for max_depth: ', x) | |
print("RMSE for train {}".format(np.sqrt(mean_squared_error(y_train, pred_dt1)))) | |
print("RMSE for test {}".format(np.sqrt(mean_squared_error(y_test, pred_dt2)))) | |
print('Accuracy Score train: ', dt.score(X_train, y_train)) | |
print('Accuracy Score test: ', dt.score(X_test, y_test)) | |
print() | |
# Decision Tree has maximum accuracy at **maximum depth 39** | |
# **Random Forest Regressor** | |
# In[ ]: | |
from sklearn.ensemble import RandomForestRegressor | |
rfc = RandomForestRegressor() | |
rfc.fit(X_train, y_train) | |
# In[ ]: | |
pred_rfc1 = rfc.predict(X_train) | |
pred_rfc2 = rfc.predict(X_test) | |
print("RMSE for train {}".format(np.sqrt(mean_squared_error(y_train, pred_rfc1)))) | |
print("RMSE for test {}".format(np.sqrt(mean_squared_error(y_test, pred_rfc2)))) | |
print('Accuracy Score train: ', dt.score(X_train, y_train)) | |
print('Accuracy Score test: ', dt.score(X_test, y_test)) | |
# In[ ]: | |
max_depth_range = np.arange(1,40,1) | |
for x in max_depth_range: | |
dt = RandomForestRegressor(max_depth= x) | |
dt.fit(X_train, y_train) | |
pred_xg1 = dt.predict(X_train) | |
pred_xg2 = dt.predict(X_test) | |
print('for max_depth: ', x) | |
print('for max_depth: ', x) | |
print("RMSE for train {}".format(np.sqrt(mean_squared_error(y_train, pred_xg1)))) | |
print("RMSE for test {}".format(np.sqrt(mean_squared_error(y_test, pred_xg2)))) | |
print('Accuracy Score train: ', dt.score(X_train, y_train)) | |
print('Accuracy Score test: ', dt.score(X_test, y_test)) | |
print() | |
# In the depth of **36** the** Random Forest Regressor** has its maximum value of accuracy. | |
# In[ ]: | |
rfc = RandomForestRegressor(max_depth = 36) | |
rfc.fit(X_train, y_train) | |
pred_rfc1 = rfc.predict(X_train) | |
pred_rfc2 = rfc.predict(X_test) | |
print("RMSE for train {}".format(np.sqrt(mean_squared_error(y_train, pred_rfc1)))) | |
print("RMSE for test {}".format(np.sqrt(mean_squared_error(y_test, pred_rfc2)))) | |
print('Accuracy Score train: ', rfc.score(X_train, y_train)) | |
print('Accuracy Score test: ', rfc.score(X_test, y_test)) | |
# **XG Boost Regressor** | |
# In[ ]: | |
from xgboost import XGBRegressor | |
xg = XGBRegressor() | |
xg.fit(X_train, y_train) | |
# In[ ]: | |
pred_xg1 = xg.predict(X_train) | |
pred_xg2 = xg.predict(X_test) | |
print("RMSE for train {}".format(np.sqrt(mean_squared_error(y_train, pred_xg1)))) | |
print("RMSE for test {}".format(np.sqrt(mean_squared_error(y_test, pred_xg2)))) | |
# In[ ]: | |
max_depth_range = np.arange(1,15,1) | |
for x in max_depth_range: | |
dt = XGBRegressor(max_depth= x) | |
dt.fit(X_train, y_train) | |
pred_xg1 = dt.predict(X_train) | |
pred_xg2 = dt.predict(X_test) | |
print('for max_depth: ', x) | |
print("RMSE for train {}".format(np.sqrt(mean_squared_error(y_train, pred_xg1)))) | |
print("RMSE for test {}".format(np.sqrt(mean_squared_error(y_test, pred_xg2)))) | |
print('Accuracy Score train: ', dt.score(X_train, y_train)) | |
print('Accuracy Score test: ', dt.score(X_test, y_test)) | |
print() | |
# It means **maximun depth 9** has best value of Accuracy | |
# In[ ]: | |
xg = XGBRegressor(max_depth = 9) | |
xg.fit(X_train, y_train) | |
pred_xg1 = xg.predict(X_train) | |
pred_xg2 = xg.predict(X_test) | |
print("RMSE for train {}".format(np.sqrt(mean_squared_error(y_train, pred_xg1)))) | |
print("RMSE for test {}".format(np.sqrt(mean_squared_error(y_test, pred_xg2)))) | |
print('Accuracy Score train: ', xg.score(X_train, y_train)) | |
print('Accuracy Score test: ', xg.score(X_test, y_test)) | |
# In[ ]: | |
tabel1 = { | |
'Train Score': [0.9679040861170889, 0.9637587048322853, 0.9601543222728802], | |
'Test Score' : [0.8808466556220073, 0.9028060343874318, 0.9115195955339979], | |
'Train RMSE' : [0.02816270639447925, 0.02992618589836856, 0.03137907401148098], | |
'Test RMSE' : [0.05659037012899937, 0.051110374979016944, 0.04876553192516943] | |
} | |
# In[ ]: | |
df1 = pd.DataFrame(tabel1) | |
# In[ ]: | |
df1 | |
# In[ ]: | |
df1.index = ['Decision Tree', 'Random Forest', 'XGBoost'] | |
# In[ ]: | |
df1 | |
# Among the method XGBoost is the best method for the data set | |
# By Comparising the Linear and XGBoost we can conclude that linear Regression the best suited for the above data set | |
# In[ ]: | |