import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import seaborn as sns
import matplotlib.pyplot as plt
from collections import Counter
# 输入数据文件可在"input/" 目录
# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory
from subprocess import check_output
# Any results you write to the current directory are saved as output.
median_house_hold_in_come = pd.read_csv('input/MedianHouseholdIncome2015.csv', encoding="windows-1252")
percentage_people_below_poverty_level = pd.read_csv('input/PercentagePeopleBelowPovertyLevel.csv', encoding="windows-1252")
percent_over_25_completed_highSchool = pd.read_csv('input/PercentOver25CompletedHighSchool.csv', encoding="windows-1252")
share_race_city = pd.read_csv('input/ShareRaceByCity.csv', encoding="windows-1252")
kill = pd.read_csv('input/PoliceKillingsUS.csv', encoding="windows-1252")
print(percentage_people_below_poverty_level.head())
print(percentage_people_below_poverty_level.info())
print(percentage_people_below_poverty_level['Geographic Area'].unique())
percentage_people_below_poverty_level.poverty_rate.replace(['-'],0.0,inplace = True)
percentage_people_below_poverty_level.poverty_rate = percentage_people_below_poverty_level.poverty_rate.astype(float)
area_list = list(percentage_people_below_poverty_level['Geographic Area'].unique())
area_poverty_ratio = []
for i in area_list:
x = percentage_people_below_poverty_level[percentage_people_below_poverty_level['Geographic Area']==i]
area_poverty_rate = sum(x.poverty_rate)/len(x)
area_poverty_ratio.append(area_poverty_rate)
data = pd.DataFrame({'area_list': area_list,'area_poverty_ratio':area_poverty_ratio})
new_index = (data['area_poverty_ratio'].sort_values(ascending=False)).index.values
sorted_data = data.reindex(new_index)
# visualization
plt.figure(figsize=(15,10))
sns.barplot(x=sorted_data['area_list'], y=sorted_data['area_poverty_ratio'])
plt.xticks(rotation= 45)
plt.xlabel('States')
plt.ylabel('Poverty Rate')
plt.title('Poverty Rate Given States')
plt.show()
print(kill.head())
separate = kill.name[kill.name != 'TK TK'].str.split()
a,b = zip(*separate)
name_list = a+b
name_count = Counter(name_list)
most_common_names = name_count.most_common(15)
x,y = zip(*most_common_names)
x,y = list(x),list(y)
plt.figure(figsize=(15,10))
ax= sns.barplot(x=x, y=y,palette = sns.cubehelix_palette(len(x)))
plt.xlabel('Name or Surname of killed people')
plt.ylabel('Frequency')
plt.title('Most common 15 Name or Surname of killed people')
plt.show()
想获取python学习资料的小伙伴可以加QQ：728711576
