Data Preparation¶

import pandas as pd
business_path = "/Users/donghe/Desktop/yelp_dataset/yelp_academic_dataset_business.json"
df_business = pd.read_json(business_path, lines=True)
df_business.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 160585 entries, 0 to 160584
Data columns (total 14 columns):
 #   Column        Non-Null Count   Dtype  
---  ------        --------------   -----  
 0   business_id   160585 non-null  object 
 1   name          160585 non-null  object 
 2   address       160585 non-null  object 
 3   city          160585 non-null  object 
 4   state         160585 non-null  object 
 5   postal_code   160585 non-null  object 
 6   latitude      160585 non-null  float64
 7   longitude     160585 non-null  float64
 8   stars         160585 non-null  float64
 9   review_count  160585 non-null  int64  
 10  is_open       160585 non-null  int64  
 11  attributes    145593 non-null  object 
 12  categories    160470 non-null  object 
 13  hours         133244 non-null  object 
dtypes: float64(3), int64(2), object(9)
memory usage: 17.2+ MB

df_business.describe()
df_business.isna().sum() / len(df_business)

business_id     0.000000
name            0.000000
address         0.000000
city            0.000000
state           0.000000
postal_code     0.000000
latitude        0.000000
longitude       0.000000
stars           0.000000
review_count    0.000000
is_open         0.000000
attributes      0.093359
categories      0.000716
hours           0.170259
dtype: float64

# Formalizing the datatypes
df_business['business_id'] = df_business['business_id'].astype("str")
df_business['name'] = df_business['name'].astype("str")
df_business['address'] = df_business['address'].astype("str")
df_business['city'] = df_business['city'].astype("str")
df_business['state'] = df_business['state'].astype("str")
df_business['latitude'] = df_business['latitude'].astype('float64')
df_business['longitude'] = df_business['longitude'].astype('float64')
df_business['stars'] = df_business['stars'].astype('float64')
df_business['review_count'] = df_business['review_count'].astype('int64')
df_business['is_open'] = df_business['is_open'].astype('bool')
df_business['attributes'] = df_business['attributes'].astype("str")
df_business['categories'] = df_business['categories'].astype("str")
df_business['hours'] = df_business['hours'].astype("str")

df_business.info()
df_business.isna().sum() / len(df_business)

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 160585 entries, 0 to 160584
Data columns (total 14 columns):
 #   Column        Non-Null Count   Dtype  
---  ------        --------------   -----  
 0   business_id   160585 non-null  object 
 1   name          160585 non-null  object 
 2   address       160585 non-null  object 
 3   city          160585 non-null  object 
 4   state         160585 non-null  object 
 5   postal_code   160585 non-null  object 
 6   latitude      160585 non-null  float64
 7   longitude     160585 non-null  float64
 8   stars         160585 non-null  float64
 9   review_count  160585 non-null  int64  
 10  is_open       160585 non-null  bool   
 11  attributes    160585 non-null  object 
 12  categories    160585 non-null  object 
 13  hours         160585 non-null  object 
dtypes: bool(1), float64(3), int64(1), object(9)
memory usage: 16.1+ MB

business_id     0.0
name            0.0
address         0.0
city            0.0
state           0.0
postal_code     0.0
latitude        0.0
longitude       0.0
stars           0.0
review_count    0.0
is_open         0.0
attributes      0.0
categories      0.0
hours           0.0
dtype: float64

Exploratory Visual Analysis¶

Initial Questions¶

How are rating stars distributed in Austin?
How do rating stars correlate with different attributes of food businesses in Austin?
How do combinations of different attributes impact rating stars of food businesses in Austin?

df_business = df_business.loc[df_business['city'] == "Austin"]
df_business.head(2)

import altair as alt
alt.data_transformers.disable_max_rows()

DataTransformerRegistry.enable('default')

Counts of open businesses and closed businesses

alt.Chart(df_business).mark_bar().encode(
    x=alt.X("is_open:N", title="Business Open?"),
    y=alt.Y("count()", title="Business Count"),
).properties(
    title="Counts of businesses: open or not"
)

	business_id	name	address	city	state	postal_code	latitude	longitude	stars	review_count	is_open	attributes	categories	hours
8	N3_Gs3DnX4k9SgpwJxdEfw	Lane Wells Jewelry Repair	7801 N Lamar Blvd, Ste A140	Austin	TX	78752	30.346169	-97.711458	5.0	30	True	{'RestaurantsPriceRange2': '1', 'ByAppointment...	Shopping, Jewelry Repair, Appraisal Services, ...	{'Monday': '12:15-17:0', 'Tuesday': '12:15-17:...
9	tXvdYGvlEceDljN8gt2_3Q	Capital City Barber Shop	615 W Slaughter Ln, Ste 113	Austin	TX	78748	30.172706	-97.799920	4.0	5	False	{'BusinessAcceptsCreditCards': 'False', 'Resta...	Barbers, Beauty & Spas	{'Monday': '9:0-17:0', 'Tuesday': '9:0-19:0', ...