#Importing Libraries
import numpy as np #NumPy is a general-purpose array-processing package.
import pandas as pd #It contains high-level data structures and manipulation tools designed to make data analysis fast and easy.
import matplotlib.pyplot as plt #It is a Plotting Library
import seaborn as sns #Seaborn is a Python data visualization library based on matplotlib.
from sklearn.linear_model import LogisticRegression #Logistic Regression is a Machine Learning classification algorithm
from sklearn.linear_model import LinearRegression #Linear Regression is a Machine Learning classification algorithm
from sklearn.model_selection import train_test_split #Splitting of Dataset
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import r2_score
#reading the dataset
zomato_orgnl=pd.read_csv("../input/zomato-bangalore-restaurants/zomato.csv")
zomato_orgnl.head() #This function returns the first n rows for the object based on position.
#Deleting Unnnecessary Columns
zomato=zomato_orgnl.drop(['url','dish_liked','phone'],axis=1)
#Removing the Duplicates
zomato.duplicated().sum()
zomato.drop_duplicates(inplace=True)
#Remove the NaN values from the dataset
zomato.isnull().sum()
zomato.dropna(how='any',inplace=True)
zomato.info()
#Changing the Columns Names
zomato.columns
zomato = zomato.rename(columns={'approx_cost(for two people)':'cost','listed_in(type)':'type',
'listed_in(city)':'city'})
zomato.columns
#Some Transformations
zomato['cost'] = zomato['cost'].astype(str)
zomato['cost'] = zomato['cost'].apply(lambda x: x.replace(',','.'))
zomato['cost'] = zomato['cost'].astype(float)
zomato.info()
#Removing '/5' from Rates
zomato['rate'].unique()
zomato = zomato.loc[zomato.rate !='NEW']
zomato = zomato.loc[zomato.rate !='-'].reset_index(drop=True)
remove_slash = lambda x: x.replace('/5', '') if type(x) == np.str else x
zomato.rate = zomato.rate.apply(remove_slash).str.strip().astype('float')
zomato['rate'].head()
#Encode the input Variables
def Encode(zomato):
for column in zomato.columns[~zomato.columns.isin(['rate', 'cost', 'votes'])]:
zomato[column] = zomato[column].factorize()[0]
return zomato
zomato_en = Encode(zomato.copy())
#Get Correlation between different variables
corr = zomato_en.corr(method='kendall')
plt.figure(figsize=(15,8))
sns.heatmap(corr, annot=True)
zomato_en.columns
#Defining the independent variables and dependent variables
x = zomato_en.iloc[:,[2,3,5,6,7,8,9,11]]
y = zomato_en['rate']
#Getting Test and Training Set
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=.1,random_state=353)
x_train.head()
y_train.head()
#Prepare a Linear REgression Model
reg=LinearRegression()
reg.fit(x_train,y_train)
y_pred=reg.predict(x_test)
from sklearn.metrics import r2_score
r2_score(y_test,y_pred)
#Prepairng a Decision Tree Regression
from sklearn.tree import DecisionTreeRegressor
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=.1,random_state=105)
DTree=DecisionTreeRegressor(min_samples_leaf=.0001)
DTree.fit(x_train,y_train)
y_predict=DTree.predict(x_test)
from sklearn.metrics import r2_score
r2_score(y_test,y_predict)
#Preparing Random Forest REgression
from sklearn.ensemble import RandomForestRegressor
RForest=RandomForestRegressor(n_estimators=500,random_state=329,min_samples_leaf=.0001)
RForest.fit(x_train,y_train)
y_predict=RForest.predict(x_test)
from sklearn.metrics import r2_score
r2_score(y_test,y_predict)
#Restaurants delivering Online or not
sns.countplot(zomato['online_order'])
fig = plt.gcf()
fig.set_size_inches(10,10)
plt.title('Restaurants delivering online or Not')
#Restaurants allowing table booking or not
sns.countplot(zomato['book_table'])
fig = plt.gcf()
fig.set_size_inches(10,10)
plt.title('Restaurants allowing table booking or not')
#Table booking Rate vs Rate
plt.rcParams['figure.figsize'] = (13, 9)
Y = pd.crosstab(zomato['rate'], zomato['book_table'])
Y.div(Y.sum(1).astype(float), axis = 0).plot(kind = 'bar', stacked = True,color=['red','yellow'])
plt.title('table booking vs rate', fontweight = 30, fontsize = 20)
plt.legend(loc="upper right")
plt.show()
# Location
sns.countplot(zomato['city'])
sns.countplot(zomato['city']).set_xticklabels(sns.countplot(zomato['city']).get_xticklabels(), rotation=90, ha="right")
fig = plt.gcf()
fig.set_size_inches(13,13)
plt.title('Location')
#Location and Rating
loc_plt=pd.crosstab(zomato['rate'],zomato['city'])
loc_plt.plot(kind='bar',stacked=True);
plt.title('Location - Rating',fontsize=15,fontweight='bold')
plt.ylabel('Location',fontsize=10,fontweight='bold')
plt.xlabel('Rating',fontsize=10,fontweight='bold')
plt.xticks(fontsize=10,fontweight='bold')
plt.yticks(fontsize=10,fontweight='bold');
plt.legend().remove();
#Type and Rating
type_plt=pd.crosstab(zomato['rate'],zomato['type'])
type_plt.plot(kind='bar',stacked=True);
plt.title('Type - Rating',fontsize=15,fontweight='bold')
plt.ylabel('Type',fontsize=10,fontweight='bold')
plt.xlabel('Rating',fontsize=10,fontweight='bold')
plt.xticks(fontsize=10,fontweight='bold')
plt.yticks(fontsize=10,fontweight='bold');
