import pandas as pd
rng = np.random.RandomState(0)
x = np.linspace(0, 10, 500)
y = np.cumsum(rng.rand(500, 6),0)
data = np.random.multivariate_normal([0,0], [[5,2],[2,2]], size=2000)
data = pd.DataFrame(data, columns=['x', 'y'])
data.head()
# KD Plot with normal distrubution
for col in 'xy':
sns.kdeplot(data[col], shade=True)
sns.distplot(data['x'])
sns.distplot(data['y'])
with sns.axes_style('white'):
sns.jointplot("x", "y", data, kind="kde")
# joint plot using seaborn
with sns.axes_style('white'):
sns.jointplot("x", "y", data, kind="hex")
tips = sns.load_dataset('tips')
tips.head()
with sns.axes_style(style='ticks'):
g = sns.factorplot("day", "total_bill", "sex", data=tips,kind="box")
g.set_axis_labels("Day","Total Bill");
with sns.axes_style('white'):
sns.jointplot("total_bill", "tip", data=tips, kind="hex")
sns.jointplot("total_bill", "tip", data=tips)
planets = sns.load_dataset("planets")
planets.head()
with sns.axes_style(style='ticks'):
g = sns.factorplot("year", data=planets, aspect = 2,kind="count", color="steelblue")
g.set_xticklabels(step=5)
Bengaluru 레스토랑 자료를 이용하여 각 레스토랑의 평균 평점(Rating)의 분포 (Data: Zomato)
5만 건 이상의 자료가 있음
# Columns Description
1. url contains the url of the restaurant in the zomato website 2. address contains the address of the restaurant in Bengaluru 3. name contains the name of the restaurant 4. online_order whether online ordering is available in the restaurant or not 5. book_table table book option available or not 6. rate contains the overall rating of the restaurant out of 5 7. votes contains total number of rating for the restaurant as of the above mentioned date 8. phone contains the phone number of the restaurant 9. location contains the neighborhood in which the restaurant is located 10. rest_type restaurant type 11. dish_liked dishes people liked in the restaurant 12. cuisines food styles, separated by comma 13. approx_cost(for two people) contains the approximate cost for meal for two people 14. reviews_list list of tuples containing reviews for the restaurant, each tuple 15. menu_item contains list of menus available in the restaurant 16. listed_in(type) type of meal 17. listed_in(city) contains the neighborhood in which the restaurant is listed
# import
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
### so that u dont have warnings
from warnings import filterwarnings
filterwarnings('ignore')
feature_na=[feature for feature in df.columns if df[feature].isnull().sum()>0]
feature_na
for feature in feature_na:
print('{} has {} % missing values'.format(feature,np.round(df[feature].isnull().sum()/len(df)*100,4)))
['rate', 'phone', 'location', 'rest_type', 'dish_liked', 'cuisines', 'approx_cost(for two people)']
#% of missing values
for feature in feature_na:
print('{} has {} % missing values'.format(feature,np.round(df[feature].isnull().sum()/len(df)*100,4)))
df['rate'].unique()
rate has 15.0337 % missing values phone has 2.3358 % missing values location has 0.0406 % missing values rest_type has 0.4389 % missing values dish_liked has 54.2916 % missing values cuisines has 0.087 % missing values approx_cost(for two people) has 0.669 % missing values
plt.figure(figsize=(10,7))
chains=df['name'].value_counts()[0:20]
sns.barplot(x=chains,y=chains.index,palette='deep')
plt.title("Most famous restaurants chains in Bangaluru")
plt.xlabel("Number of outlets")
레스토랑 체인 이름과 개수 담겨있음
How many of the restuarants do not accept online orders?
x=df['online_order'].value_counts()
x
labels=['accepted','not accepted']
plt.pie(x,explode=[0.0,0.1],autopct='%1.1f%%')
Yes 28308 No 15634 Name: online_order, dtype: int64
