python数据分析

import matplotlib.pyplot as plt
import pandas as pd
datafile = 'air_data.csv'
resultfile = 'explore.csv'

data = pd.read_csv(datafile,encoding='utf-8')

explore = data.describe(percentiles=[],include='all').T

explore['null'] = len(data) - explore['count']
explore = explore[['null','max','min']]

explore.columns = [u'空数值',u'最大值',u'最小值']

explore.to_csv(resultfile)

from datetime import datetime
ffp = data['FFP_DATE'].apply(lambda x:datetime.strptime(x,'%Y/%m/%d'))
ffp_year = ffp.map(lambda x:x.year)
fig = plt.figure(figsize=(8,5))
plt.rcParams['font.sans-serif'] = 'SimHei'
plt.rcParams['axes.unicode_minus'] = False
plt.hist(ffp_year,bins='auto',color='#0504aa')
plt.xlabel('年份')
plt.ylabel('入会人数')
plt.title('各年份会员人数 学号3119')

plt.show()

plt.close()

#提取会员不同性别人数
male = pd.value_counts(data['GENDER'])['男']
female = pd.value_counts(data['GENDER'])['女']
#绘制会员性别比例饼图
fig = plt.figure(figsize=(7, 4))  #设置画布大小
plt.pie([male, female], labels=['男', '女'], colors=['lightskyblue', 'lightcoral'], autopct='%1.1f%%')
plt.title('会员性别比例 学号3119')
plt.show()
plt.close()

 

 

 

#提取会员年龄
age=data['AGE'].dropna()
age=age.astype('int64')
#绘制会员年龄分布箱型图
fig=plt.figure(figsize=(5,10))
plt.boxplot(age,patch_artist=True,labels=['会员年龄'],boxprops={'facecolor':'lightblue'})
plt.title('会员年龄分布箱型图学号3119')
plt.grid(axis='y')
plt.show()
plt.close

 

 

#提取不同级别会员的人数
lv_four=pd.value_counts(data['FFP_TIER'])[4]
lv_five=pd.value_counts(data['FFP_TIER'])[5]
lv_six=pd.value_counts(data['FFP_TIER'])[6]
#绘制会员各级别人数条形图
fig=plt.figure(figsize=(8,5))
plt.bar(x=range(3),height=[lv_four,lv_five,lv_six],width=0.4,alpha=0.8,color='skyblue')
plt.xticks([index for index in range(3)],['4','5','6'])
plt.xlabel('会员等级')
plt.ylabel('会员人数')
plt.title('会员各级别人数学号3119')
plt.show()
plt.close()