#Importing the necessary libraries import pandas as pd from sklearn.linear_model import LinearRegression from sklearn.metrics import mean_squared_error import numpy as np from sklearn.preprocessing import LabelEncoder import matplotlib.pyplot as plt import seaborn as sns

#Import the training and testing datasets train_data = pd.read_csv('train_kOBLwZA.csv') test_data = pd.read_csv('test_t02dQwI.csv')

train_data.columns

train_data.info()

train_data.describe()

train_data['Item_Fat_Content'].unique()

sns.boxplot(x=train_data.Item_Fat_Content, y=train_data.Item_Outlet_Sales);

sns.boxplot(x=train_data.Outlet_Location_Type, y=train_data.Item_Outlet_Sales);

train_data['Item_Type'].unique()

plt.figure(figsize=(22,7)) sns.boxplot(x=train_data.Item_Type, y=train_data.Item_Outlet_Sales);

sns.boxplot(x=train_data.Outlet_Size, y=train_data.Item_Outlet_Sales);

plt.figure(figsize=(10,5)) sns.boxplot(x=train_data.Outlet_Type, y=train_data.Item_Outlet_Sales);

features= ['Outlet_Type', 'Item_Type'] fig= plt.subplots(figsize= (15,30)) for i,j in enumerate(features): plt.subplot(4,2, i+1) plt.subplots_adjust(hspace=1.0) sns.countplot(x=j, data=train_data , hue= "Outlet_Location_Type") plt.xticks(rotation= 90) plt.title("No of Items")

content= {'Low Fat': 1, 'Regular': 0, 'low fat': 1,'LF': 1, 'reg':0 } data = [train_data, test_data] for dataset in data: dataset['Item_Fat_Content'] = dataset['Item_Fat_Content'].map(content)

train_data['Outlet_Location_Type'].unique()

location= {'Tier 1': 1, 'Tier 2': 2, 'Tier 3': 3 } data = [train_data, test_data] for dataset in data: dataset['Outlet_Location_Type'] = dataset['Outlet_Location_Type'].map(location)

from sklearn.preprocessing import OneHotEncoder one_hot = pd.get_dummies(train_data['Item_Type']) # Drop column B as it is now encoded train_data = train_data.drop('Item_Type',axis = 1) # Join the encoded df train_data= train_data.join(one_hot)

from sklearn.preprocessing import OneHotEncoder one_hot = pd.get_dummies(test_data['Item_Type']) # Drop column B as it is now encoded test_data = test_data.drop('Item_Type',axis = 1) # Join the encoded df test_data= test_data.join(one_hot)

train_data['Outlet_Size'].unique()

train_data["Outlet_Size"]= train_data["Outlet_Size"].fillna("Medium") test_data["Outlet_Size"]= test_data["Outlet_Size"].fillna("Medium") encode = LabelEncoder() train_data.Outlet_Size = encode.fit_transform(train_data.Outlet_Size) test_data.Outlet_Size = encode.fit_transform(test_data.Outlet_Size)

train_data["Item_Weight"]= train_data["Item_Weight"].fillna(12.6) test_data["Item_Weight"]= test_data["Item_Weight"].fillna(12.6)

train_data['Outlet_Type'].unique()

storetype= {'Supermarket Type1': 3, 'Supermarket Type2': 2, 'Grocery Store': 1,'Supermarket Type3': 4} data = [train_data, test_data] for dataset in data: dataset['Outlet_Type'] = dataset['Outlet_Type'].map(storetype)

print('\nShape of training data :',train_data.shape) print('\nShape of testing data :',test_data.shape)

train_x = train_data.drop(columns=["Item_Identifier","Outlet_Identifier",'Item_Outlet_Sales'],axis=1) train_y = train_data['Item_Outlet_Sales']

from sklearn.model_selection import train_test_split x_train,x_test,y_train,y_test=train_test_split(train_x,train_y,test_size=0.25,random_state=42)

model = LinearRegression() model.fit(train_x,train_y)

print('\nCoefficient of model :', model.coef_)

print('\nIntercept of model',model.intercept_)

predict_train = model.predict(train_x) print('\nItem_Outlet_Sales on training data',predict_train)

predict_test = model.predict(x_test) print('\nItem_Outlet_Sales on test data',predict_test)

rmse_train = mean_squared_error(train_y,predict_train)**(0.5) print('\nRMSE on train dataset : ', rmse_train)

rmse_test = mean_squared_error(y_test,predict_test)**(0.5) print('\nRMSE on test dataset : ', rmse_test)