python | 工作笔记 | pandas 常用总结

## 方法一：全部修改
df.columns = ['a', 'b', 'c', 'd']
df.columns = df.columns.map(lambda x:x[1:])
df.columns = df.columns.str.strip('$')
## 方法二：可以局部修改
df.rename(columns=('$a': 'a','$e': 'e'}, inplace=True)
df.rename(columns=lambda x:x.replace('$',''), inplace=True)

## concat拼接，我常用于处理单个列或行后将数据拼接在一起。
hangye_shouyi_ratio = pd.DataFrame()
for i in range(1,16):
    data_hangye_indexa = hangye_index.iloc[:,i+1].values - hangye_index.iloc[:,i].values
    hangye_shouyi_ratio = pd.concat([hangye_shouyi_ratio,data_hangye_indexa.T],axis=0)

# 基于关键词"申万一级行业"拼接两个dataframe
pd.merge(hangye_index,chaopei,on='申万一级行业')

## 计算NAN或缺失值的个数
df.isnull().sum(axis=1)
## 计算非NAN或缺失值的个数
df.null().sum(axis=1)

## 排序，降序
table4.sort_values(by='区间累计涨跌幅',ascending=False)

## duplicated
falsei = []
for i,x in enumerate(data_liutong.duplicated(keep = 'first')):
    if x == False:
        falsei.append(i)
data_liutong = data_liutong.iloc[falsei,:]
data_liutong.head(10)  

## 建议把这些内容复制过去，可以保证后面有问题的都可以解决掉
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
from matplotlib.pylab import mpl
mpl.rcParams['axes.unicode_minus'] = False  # 解决负号显示异常的问题
my_font = FontProperties(fname=r"C:\\Windows\\fonts\\SimHei.ttf")  # 使用指定中文字体
plt.rc('font', family='SimHei', size=8)

## 重点：twinx
import matplotlib.pyplot as plt
import numpy as np
plt.clf()  # 清空画布
fig  = plt.figure(figsize=(8,4))


x = pd.date_range('31/3/2013','30/9/2016',freq='3M')
data_stock_hangye_sum_ratio[data_stock_hangye_sum_ratio.index == '计算机'].values[0]

y1 = hangye_index[hangye_index.iloc[:,0] == '计算机'].iloc[:,2:17].values[0]
y2 = data_stock_hangye_sum_ratio[data_stock_hangye_sum_ratio.index == '计算机'].values[0]

ax1 = fig.add_subplot(111)
ax1.plot(x,hangye_index[hangye_index.iloc[:,0] == '计算机'].iloc[:,2:17].values[0])
ax1.set_ylabel('计算机行业指数走势')
ax1.set_title('计算机行业行情走势与基金持仓占比变化')
ax2 = ax1.twinx()

ax2.plot(x,data_stock_hangye_sum_ratio[data_stock_hangye_sum_ratio.index == '计算机'].values[0],'r')
#ax2.set_xlim(x)
ax2.set_ylabel('计算机行业基金持仓占比')
ax2.set_xlabel('时间')

plt.show()

for i,x enumerate(data):
   print(i)
   print (x)

## 先将时间的格式统一处理下，再来转换格式
print (datetime.strptime('2013-03-29 0:00',"%Y-%m-%d %H:%M").strftime("%Y-%m-%d"))

import pandas as pd
from datetime import datetime
cal_date = pd.read_csv("D:\\python\\Scripts\\cal_date.csv")
## 几月
cal_date['month'] = pd.DatetimeIndex(cal_date.calendarDate).month
## 周几
cal_date['day'] = pd.DatetimeIndex(cal_date.calendarDate).dayofweek
## 这个月的第几周
cal_date['week'] = pd.DatetimeIndex(cal_date.calendarDate).week

import matplotlib.pyplot as plt
import numpy as np

x = np.arange(0., np.e, 0.01)
y1 = np.exp(-x)
y2 = np.log(x)

fig = plt.figure()

ax1 = fig.add_subplot(111)
# ax1 = plt.plot()
ax1.plot(x, y1)
ax1.set_ylabel('Y values for exp(-x)')
ax1.set_title("Double Y axis")

ax2 = ax1.twinx()  # this is the important function
ax2.plot(x, y2, 'r')
ax2.set_xlim([0, np.e])
ax2.set_ylabel('Y values for ln(x)')
ax2.set_xlabel('Same X for both exp(-x) and ln(x)')

plt.show()

import matplotlib.font_manager as fm
myfont = fm.FontProperties(fname='C:/Windows/Fonts/msyh.ttc')
import matplotlib.pyplot as plt
import numpy as np
plt.rc('font', family='SimHei', size=8)
import matplotlib.pyplot as plt

### 第一张图
plt.clf()  # 清空画布
plt.figure(figsize=(16,64),dpi=80) 

plt.subplot(8,2,1)
plt.pie(data_stock_hangye_sum_ratio.mean(axis = 1).values,labels=labels,autopct='%1.1f%%',shadow=False, startangle=90,pctdistance = 1.06)
plt.ylabel("基金重仓持股行业平均占比情况(2013Q1-2016Q3)",fontproperties=myfont)

# 第二张图
for i in range(len(date)):
    numbers = int(i + 2)
    plt.subplot(8,2,numbers)
    plt.pie(data_stock_hangye_sum_ratio.iloc[:,i].values,labels=labels,
            autopct='%1.1f%%',shadow=False, startangle=90,pctdistance = 1.06)
    #plt.xlabel("基金重仓持股行业平均占比情况(2013Q1-2016Q3)",fontproperties=myfont)
    plt.ylabel("基金重仓持股行业平均占比情况 "+ date[i],fontproperties=myfont)

plt.show()

import matplotlib.pyplot as plt
import numpy as np
import numpy.random as rnd


def f(t):
    s1 = np.sin(2 * np.pi * t)
    e1 = np.exp(-t)
    return np.absolute((s1 * e1)) + .05

t = np.arange(0.0, 5.0, 0.1)
s = f(t)
nse = rnd.normal(0.0, 0.3, t.shape) * s

fig = plt.figure(figsize=(12, 6))
vax = fig.add_subplot(121)
hax = fig.add_subplot(122)

vax.plot(t, s + nse, '^')
vax.vlines(t, [0], s)
vax.set_xlabel('time (s)')
vax.set_title('Vertical lines demo')

hax.plot(s + nse, t, '^')
hax.hlines(t, [0], s, lw=2)
hax.set_xlabel('time (s)')
hax.set_title('Horizontal lines demo')

plt.show()