Zomato.py

#Deleting Unnnecessary Columns
zomato=zomato_real.drop(['url','dish_liked','phone'],axis=1) #Dropping the column "dish_liked", "phone", "url" and saving the new dataset as "zomato"

#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)

#Changing the column names
zomato = zomato.rename(columns={'approx_cost(for two people)':'cost','listed_in(type)':'type', 'listed_in(city)':'city'})

#Some Transformations
zomato['cost'] = zomato['cost'].astype(str) #Changing the cost to string
zomato['cost'] = zomato['cost'].apply(lambda x: x.replace(',','.')) #Using lambda function to replace ',' from cost
zomato['cost'] = zomato['cost'].astype(float)
#Removing '/5' from Rates
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')

# Adjust the column names
zomato.name = zomato.name.apply(lambda x:x.title())
zomato.online_order.replace(('Yes','No'),(True, False),inplace=True)
zomato.book_table.replace(('Yes','No'),(True, False),inplace=True)

## Computing Mean Rating
restaurants = list(zomato['name'].unique())
zomato['Mean Rating'] = 0

for i in range(len(restaurants)):
    zomato['Mean Rating'][zomato['name'] == restaurants[i]] = zomato['rate'][zomato['name'] == restaurants[i]].mean()
    
from sklearn.preprocessing import MinMaxScaler
scaler = MinMaxScaler(feature_range = (1,5))
zomato[['Mean Rating']] = scaler.fit_transform(zomato[['Mean Rating']]).round(2)