#import libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

#Create a dataframe
df=pd.read_csv("E:\dataset\zomato.csv",encoding='latin-1')
df.head()

Output:

df.shape

Output:

(9551, 21)

df.columns

Output:

Index(['Restaurant ID', 'Restaurant Name', 'Country Code', 'City', 'Addres s', 'Locality', 'Locality Verbose', 'Longitude', 'Latitude', 'Cuisines', 'Average Cost for two', 'Currency', 'Has Table booking', 'Has Online delivery', 'Is delivering now', 'Switch to order menu', 'Price range', 'Aggregate rating', 'Rating color', 'Rating text', 'Votes'], dtype='object')

df.info()

df.describe()

Output:

#Get missing values
df.isnull().sum()

Output:

[k for k in df.columns if df[k].isnull().sum()>0]

Output: ['Cuisines']

sns.heatmap(df.isnull(),yticklabels=False,cbar=False,cmap='viridis')

Output: <AxesSubplot:>

df_country=pd.read_excel('E:\dataset\Country-Code.xlsx')
df_country

Output:

df.columns

Output:

Index(['Restaurant ID', 'Restaurant Name', 'Country Code', 'City', 'Addres s', 'Locality', 'Locality Verbose', 'Longitude', 'Latitude', 'Cuisines', 'Average Cost for two', 'Currency', 'Has Table booking', 'Has Online delivery', 'Is delivering now', 'Switch to order menu', 'Price range', 'Aggregate rating', 'Rating color', 'Rating text', 'Votes'], dtype='object')

df1=pd.merge(df,df_country,on='Country Code',how='left')
df1.head(3)

Output:

df1.dtypes

Output:

df1.Country.value_counts()

Output:

country_names=df1.Country.value_counts().index
country_names

Output:

Index(['India', 'United States', 'United Kingdom', 'Brazil', 'South Africa', 'UAE', 'New Zealand', 'Turkey', 'Australia', 'Phillipines', 'Indonesia', 'Qatar', 'Singapore', 'Sri Lanka', 'Canada'], dtype='object')

country_values=df1.Country.value_counts().values
country_values

Output:

array([8652, 434, 80, 60, 60, 60, 40, 34, 24, 22, 21, 20, 20, 20, 4], dtype=int64)

#pie chart
plt.pie(country_values,labels=country_names)

Output:

#Top-3 conuntries that uses zomato
plt.pie(country_values[:3],labels=country_names[:3])

Output:

plt.pie(country_values[:3],labels=country_names[:3],autopct="%1.2f%%")

Output:

df1.columns

Output:

Index(['Restaurant ID', 'Restaurant Name', 'Country Code', 'City', 'Addres s', 'Locality', 'Locality Verbose', 'Longitude', 'Latitude', 'Cuisines', 'Average Cost for two', 'Currency', 'Has Table booking', 'Has Online delivery', 'Is delivering now', 'Switch to order menu', 'Price range', 'Aggregate rating', 'Rating color', 'Rating text', 'Votes', 'Country'], dtype='object')

df1.groupby(['Aggregate rating','Rating color','Rating text']).size()

Output:

ratings=df1.groupby(['Aggregate rating','Rating color','Rating text']).size().reset_index()

ratings

Output:

ratings.head()

Output:

sns.barplot(x="Aggregate rating",y="Rating Count",data=ratings)
plt.show()

Output:

import matplotlib
matplotlib.rcParams['figure.figsize']=(12,6)
sns.barplot(x="Aggregate rating",y="Rating Count",hue='Rating color',palette=['White','Blue
plt.show()

Output:

sns.countplot(x="Rating color",data=ratings,palette=['Blue','Blue','Red','Orange','Yellow',
plt.show()

Output:

#Find out the countries that has given 0 rating
df1.columns

Output:

Index(['Restaurant ID', 'Restaurant Name', 'Country Code', 'City', 'Address', 'Locality', 'Locality Verbose', 'Longitude', 'Latitude', 'Cuisines', 'Average Cost for two', 'Currency', 'Has Table booking', 'Has Online delivery', 'Is delivering now', 'Switch to order menu', 'Price range', 'Aggregate rating', 'Rating color', 'Rating text', 'Votes', 'Country'], dtype='object')

Output:

#Find out which currency is used by which country
df1.columns

Output:

Index(['Restaurant ID', 'Restaurant Name', 'Country Code', 'City', 'Addres s', 'Locality', 'Locality Verbose', 'Longitude', 'Latitude', 'Cuisines', 'Average Cost for two', 'Currency', 'Has Table booking', 'Has Online delivery', 'Is delivering now', 'Switch to order menu', 'Price range', 'Aggregate rating', 'Rating color', 'Rating text', 'Votes', 'Country'], dtype='object')

df1[['Country','Currency']].groupby(['Country','Currency']).size().reset_index()

Output:

#Which countries do have online delivery
df1[df1['Has Online delivery']=='Yes'].Country.value_counts()

Output:

India 2423
UAE      28
Name: Country, dtype: int64

df1[['Has Online delivery','Country']].groupby(['Has Online delivery','Country']).size().re

Output:

#Create a pie chart for top-5 cities distribution
df1.columns

Output:

Index(['Restaurant ID', 'Restaurant Name', 'Country Code', 'City', 'Addres s', 'Locality', 'Locality Verbose', 'Longitude', 'Latitude', 'Cuisines', 'Average Cost for two', 'Currency', 'Has Table booking', 'Has Online delivery', 'Is delivering now', 'Switch to order menu', 'Price range', 'Aggregate rating', 'Rating color', 'Rating text', 'Votes', 'Country'], dtype='object')

df1.City.value_counts().index

Output:

Index(['New Delhi', 'Gurgaon', 'Noida', 'Faridabad', 'Ghaziabad', 'Ahmedabad', 'Guwahati', 'Lucknow', 'Amritsar', 'Bhubaneshwar', ... 'Dicky Beach', 'Forrest', 'Vineland Station', 'Potrero', 'Mohali', 'Lakes Entrance', 'Bandung', 'Huskisson', 'Princeton', 'Lincoln'], dtype='object', length=141)

city_values=df1.City.value_counts().values
city_labels=df1.City.value_counts().index

plt.pie(city_values[:5],labels=city_labels[:5])

Output:

([<matplotlib.patches.Wedge at 0x192866bc400>, <matplotlib.patches.Wedge at 0x192866bc190>, <matplotlib.patches.Wedge at 0x192866e8c70>, <matplotlib.patches.Wedge at 0x192866e84c0>, <matplotlib.patches.Wedge at 0x192866e8820>], [Text(-0.6145352824185932, 0.9123301960708633, 'New Delhi'), Text(0.0623675251198054, -1.0982305276263407, 'Gurgaon'), Text(0.8789045225625368, -0.6614581167535246, 'Noida'), Text(1.0922218418223437, -0.13058119407559224, 'Faridabad'), Text(1.099946280005612, -0.010871113182029924, 'Ghaziabad')])

plt.pie(city_values[:5],labels=city_labels[:5],autopct='%1.2f%%')

Output:

([<matplotlib.patches.Wedge at 0x19285c4c4f0>, <matplotlib.patches.Wedge at 0x19285c4c7f0>, <matplotlib.patches.Wedge at 0x19285c4c790>, <matplotlib.patches.Wedge at 0x19285c158e0>, <matplotlib.patches.Wedge at 0x19285c152b0>], [Text(-0.6145352824185932, 0.9123301960708633, 'New Delhi'), Text(0.0623675251198054, -1.0982305276263407, 'Gurgaon'), Text(0.8789045225625368, -0.6614581167535246, 'Noida'), Text(1.0922218418223437, -0.13058119407559224, 'Faridabad'), Text(1.099946280005612, -0.010871113182029924, 'Ghaziabad')], [Text(-0.3352010631374145, 0.497634652402289, '68.87%'), Text(0.0340186500653484, -0.5990348332507311, '14.07%'), Text(0.47940246685229276, -0.36079533641101336, '13.59%'), Text(0.5957573682667329, -0.07122610585941394, '3.16%'), Text(0.5999706981848791, -0.005929698099289049, '0.31%')])