How Analyzing Zomato Restaurant Data Can Help You Extract the Best Cuisines Data in Local Areas?

from google.colab import files
files.upload()
! pip install opendatasets --upgrade
import opendatasets as od
dataset_url = 'https://www.foodspark.io/archives'
od.download(dataset_url)

import pandas as pd
df = pd.read_csv('/content/zomato-restaurants-data/zomato.csv', engine='python')
df.head(2)

## Checking if dataset contains any null
nan_values = df.isna()
nan_columns = nan_values.any()
columns_with_nan = df.columns[nan_columns].tolist()
print(columns_with_nan)
['Cuisines']

df1 = pd.read_excel('/content/zomato-restaurants-data/Country-Code.xlsx')
df1.head()

df2 = pd.merge(df,df1,on='Country Code',how='left')
df2.head(2)

print('List of counteris the survey is spread accross - ')
for x in pd.unique(df2.Country): print(x)
print()
print('Total number to country', len(pd.unique(df2.Country)))

from plotly.offline import init_notebook_mode, plot, iplot
labels = list(df2.Country.value_counts().index)
values = list(df2.Country.value_counts().values)
fig = {
    "data":[
        {
            "labels" : labels,
            "values" : values,
            "hoverinfo" : 'label+percent',
            "domain": {"x": [0, .9]},
            "hole" : 0.6,
            "type" : "pie",
            "rotation":120,
        },
    ],
    "layout": {
        "title" : "Zomato's Presence around the World",
        "annotations": [
            {
                "font": {"size":20},
                "showarrow": True,
                "text": "Countries",
                "x":0.2,
                "y":0.9,
            },
        ]
    }
}
iplot(fig)

df3 = df2.groupby(['Aggregate rating','Rating color', 'Rating text']).size().reset_index().rename(columns={0:'Rating Count'})
df3
df3

import seaborn as sns
import matplotlib
import matplotlib.pyplot as plt
%matplotlib inline
sns.set_style('darkgrid')
matplotlib.rcParams['font.size'] = 14
matplotlib.rcParams['figure.figsize'] = (9, 5)
matplotlib.rcParams['figure.facecolor'] = '#00000000'
plt.figure(figsize=(12,6))
# plt.xticks(rotation=75)
plt.title('Rating Color')
sns.barplot(x=df3['Rating color'], y=df3['Rating Count']);

No_rating = df2[df2['Rating color']=='White'].groupby('Country').size().reset_index().rename(columns={0:'Rating Count'})
No_rating

plt.figure(figsize=(12,6))
plt.title('Online Delivery Distribution')
plt.pie(df2['Has Online delivery'].value_counts()/9551*100, labels=df2['Has Online delivery'].value_counts().index, autopct='%1.1f%%', startangle=180);

from plotly.offline import init_notebook_mode, plot, iplot
import plotly.graph_objs as go
plt.figure(figsize=(12,6))
# import plotly.plotly as py

labels = list(df2.City.value_counts().head(20).index)
values = list(df2.City.value_counts().head(20).values)

fig = {
    "data":[
        {
            "labels" : labels,
            "values" : values,
            "hoverinfo" : 'label+percent',
            "domain": {"x": [0, .9]},
            "hole" : 0.6,
            "type" : "pie",
            "rotation":120,
        },
    ],
    "layout": {
        "title" : "Zomato's Presence Citywise",
        "annotations": [
            {
                "font": {"size":20},
                "showarrow": True,
                "text": "Cities",
                "x":0.2,
                "y":0.9,
            },
        ]
    }
}
iplot(fig);

Delhi = df2[(df2.City == 'New Delhi')]
plt.figure(figsize=(12,6))
sns.barplot(x=Delhi.Locality.value_counts().head(10), y=Delhi.Locality.value_counts().head(10).index)

plt.ylabel(None);
plt.xlabel('Number of Resturants')
plt.title('Resturants Listing on Zomato');

# I achieve this by the following steps

## Fetching the resturants having 'Excellent' and 'Very Good' rating
ConnaughtPlace = Delhi[(Delhi.Locality.isin(['Connaught Place'])) & (Delhi['Rating text'].isin(['Excellent','Very Good']))]

ConnaughtPlace = ConnaughtPlace.Cuisines.value_counts().reset_index()

## Extracing all the cuisens in a single list
cuisien = []
for x in ConnaughtPlace['index']: 
  cuisien.append(x)

# cuisien = '[%s]'%', '.join(map(str, cuisien))
cuisien

['North Indian, Chinese, Italian, Continental',
 'North Indian',
 'North Indian, Italian, Asian, American',
 'Continental, North Indian, Chinese, Mediterranean',
 'Chinese',
 'Continental, American, Asian, North Indian',
 'North Indian, Continental',
 'Continental, Mediterranean, Italian, North Indian',
 'North Indian, European, Asian, Mediterranean',
 'Japanese',
 'Bakery, Desserts, Fast Food',
 'North Indian, Afghani, Mughlai',
 'Biryani, North Indian, Hyderabadi',
 'Ice Cream',
 'Continental, Mexican, Burger, American, Pizza, Tex-Mex',
 'North Indian, Chinese',
 'North Indian, Mediterranean, Asian, Fast Food',
 'North Indian, European',
 'Healthy Food, Continental, Italian',
 'Continental, North Indian, Italian, Asian',
 'Continental, Italian, Asian, Indian',
 'Biryani, Hyderabadi',
 'Bakery, Fast Food, Desserts',
 'Italian, Mexican, Continental, North Indian, Finger Food',
 'Cafe',
 'Asian, North Indian',
 'South Indian',
 'Modern Indian',
 'North Indian, Chinese, Continental, Italian',
 'North Indian, Chinese, Italian, American, Middle Eastern',
 'Fast Food, American, Burger']

from wordcloud import WordCloud, STOPWORDS
import matplotlib.pyplot as plt
import pandas as pd
  
comment_words = ''
stopwords = set(STOPWORDS)
  
# iterate through the csv file
for val in cuisien:
      
    # typecaste each val to string
    val = str(val)
  
    # split the value
    tokens = val.split()
      
    # Converts each token into lowercase
    for i in range(len(tokens)):
        tokens[i] = tokens[i].lower()
      
    comment_words += " ".join(tokens)+" "
  
wordcloud = WordCloud(width = 800, height = 800,
                background_color ='white',
                stopwords = stopwords,
                min_font_size = 10).generate(comment_words)
  
# plot the WordCloud image                       
plt.figure(figsize = (8, 8), facecolor = 'b', edgecolor='g')
plt.title('Resturants cuisien -  Top Resturants')
plt.imshow(wordcloud)
plt.axis("off")
plt.tight_layout(pad = 0)
  
plt.show()

top_locality = Delhi.Locality.value_counts().head(10)
sns.set_theme(style="darkgrid")
plt.figure(figsize=(12,6))
ax = sns.countplot(y= "Locality", hue="Has Online delivery", data=Delhi[Delhi.Locality.isin(top_locality.index)])
plt.title('Resturants Online Delivery');

plt.figure(figsize=(12,6))
sns.scatterplot(x="Average Cost for two", y="Aggregate rating", hue='Price range', data=Delhi)

plt.xlabel("Average Cost for two")
plt.ylabel("Aggregate rating")
plt.title('Rating vs Cost of Two');

Delhi['Rating text'].value_counts()
Average      2495
Not rated    1425
Good         1128
Very Good     300
Poor           97
Excellent      28
Name: Rating text, dtype: int64

import plotly.express as px
Highly_rated = Delhi[Delhi['Rating text'].isin(['Excellent'])]

fig = px.scatter_mapbox(Highly_rated, lat="Latitude", lon="Longitude", hover_name="City", hover_data=["Aggregate rating", "Restaurant Name"],
                        color_discrete_sequence=["fuchsia"], zoom=10, height=300)
fig.update_layout(mapbox_style="open-street-map")
fig.update_layout(margin={"r":0,"t":0,"l":0,"b":0})
fig.update_layout(title='Highle rated Resturants Location',
                  autosize=True,
                  hovermode='closest',
                  showlegend=False)
fig.update_layout(
    autosize=False,
    width=800,
    height=500,)

fig.show()

types = {
    "Breakfast and Coffee" : ["Cafe Coffee Day", "Starbucks", "Barista", "Costa Coffee", "Chaayos", "Dunkin' Donuts"],
    "American": ["Domino's Pizza", "McDonald's", "Burger King", "Subway", "Dunkin' Donuts", "Pizza Hut"],
    "Ice Creams and Shakes": ["Keventers", "Giani", "Giani's", "Starbucks", "Baskin Robbins", "Nirula's Ice Cream"]
}

breakfast = Delhi[Delhi['Restaurant Name'].isin(types['Breakfast and Coffee'])]
american = Delhi[Delhi['Restaurant Name'].isin(types['American'])]
ice_cream = Delhi[Delhi['Restaurant Name'].isin(types['Ice Creams and Shakes'])]

breakfast = breakfast[['Restaurant Name','Aggregate rating']].groupby('Restaurant Name').mean().reset_index().sort_values('Aggregate rating',ascending=False)
breakfast
https://www.foodspark.io/how-analyzing-zomato-restaurant-data-can-help-you-extract-the-best-cuisines-data-in-local-areas.php
import plotly.express as px

df= breakfast
fig = px.bar(df, y='Aggregate rating', x='Restaurant Name', text='Aggregate rating', title="Breakfast and Coffee locations")
fig.update_traces(texttemplate='%{text:.3s}', textposition='outside')
fig.update_layout(
    autosize=False,
    width=800,
    height=500,)
fig.show()

american = american[['Restaurant Name','Aggregate rating']].groupby('Restaurant Name').mean().reset_index().sort_values('Aggregate rating',ascending=False)
american

import plotly.express as px

df= american
fig = px.bar(df, y='Aggregate rating', x='Restaurant Name', text='Aggregate rating', title="Fast Food Resturants")
fig.update_traces(texttemplate='%{text:.3s}', textposition='outside')
fig.update_layout(
    autosize=False,
    width=800,
    height=500,)

fig.show()

ice_cream = ice_cream[['Restaurant Name','Aggregate rating']].groupby('Restaurant Name').mean().reset_index().sort_values('Aggregate rating',ascending=False)
ice_cream

import plotly.express as px

df= ice_cream
fig = px.bar(df, y='Aggregate rating', x='Restaurant Name', text='Aggregate rating', title="Ice Cream Parlours")
fig.update_traces(texttemplate='%{text:.3s}', textposition='outside')
fig.update_layout(
    autosize=False,
    width=800,
    height=500,)
fig.show()