数据分析

涉及内容：第一：利用pandas实现文件的读写（重点在于读取不连续的列，通过usercols()函数实现)

                  第二：对时间进行格式化

                  第三：只提取时间的年和月，然后根据月分组并求和

                  第四：利用matplotlib画柱状图（展示对比）和线性图（展示趋势）

代码如下：

#encoding:utf-8

import pandas as pd
import datetime
import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D

filePath="/Users/apple/PycharmProjects/AmericanPrisedent/presidential_polls.csv"
data = pd.read_csv(filePath,usecols=['enddate','rawpoll_clinton','adjpoll_clinton','rawpoll_trump','adjpoll_trump'])
df =pd.DataFrame(data)

df['enddate'] = pd.to_datetime(df['enddate'])
x=['%d-%02d' %(i.year,i.month)for i in df["enddate"]]
month_array = np.array(x)
df['enddate'] = x
grouped = df.groupby('enddate',as_index=False).sum().ix[:,'rawpoll_clinton':'adjpoll_trump']
fig = plt.figure()
ax1 = fig.add_subplot(2,2,1)
ax2 = fig.add_subplot(2,2,2)
ax3 = fig.add_subplot(2,2,3)
ax4 = fig.add_subplot(2,2,4)
#线性图
ax1.plot(grouped['rawpoll_clinton'],color = 'r')
ax1.plot(grouped['rawpoll_trump'],color = 'g')
# 生成柱状图
width = 0.25
x = np.arange(12)
ax2.bar(x, grouped['rawpoll_clinton'], width, color='r')
ax2.bar(x + width,grouped['rawpoll_trump'], width, color='g')
ax2.set_xticks(x + width)
ax2.set_xticklabels (('1','2','3','4','5','6','7','8','9','10','11','12'),rotation='vertical')
plt.show()