python pandas入门（1）

#_*_ coding: utf-8 _*_
import numpy as np
import pandas as pd

s= pd.Series([1,3,5,np.nan,6,8])
dates =  pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
#根据字典对象生成 DataFrame
df2 = pd.DataFrame({'A': 1.,'B':pd.Timestamp('20210123'),'C': pd.Series(1., index=list(range(0,4)), dtype='float32'),
                    'D':np.array([3]*4,dtype='int32'),'E': pd.Categorical(["test", "train", "test", "train"]),
                    'F': 'foo'},index = np.random.randint(1,9,(1,4)).ravel())
print(df.to_numpy())
# 将pandas底层数据转换成numpy类型
print(df.sort_index(axis=0,ascending=True))
# 根据索引或者column排序
print(df.sort_values(by='B',ascending=False))
# 按值排序
#
# 获取数据
print(df['A'],df[0:3],df['20210124':'20210126'],
      df.loc[dates[0]],df.loc[:,['A','B']],
      df.loc[dates[0:2],['A','B']],
      df.loc[dates[0], 'A'])
#loc是按标签选择

print(df.iloc[0],
      df.iloc[3:5, 0:2],
      df.iloc[[1, 2, 4], [0, 2]],
      df.iloc[:, 1:3],df.iloc[1, 1])

#布尔索引
print(df[df['A']>0],
      df[df > 0])
#isin筛选，跟in类似
df['E'] = ['one', 'one', 'two', 'three', 'four', 'three']
print(df[df['E'].isin(['two', 'four'])])

#赋值

#按标签赋值
df.loc[dates[0],'A'] = 0
#按位置赋值
df.iloc[1,0] = 0
#按numpy数组赋值
df.loc[:,'D'] = np.array([5.]*len(df))

#删除列
df= df.drop(columns=['E'])

#重建索引
df1 = df.reindex(index=dates[0:4], columns=list(df.columns) + ['E'])
df1.loc[dates[0]:dates[1], 'E'] = 1

#删除所有缺失值的行
df1.dropna(how ='any')

#补充缺失值
df1.fillna(value=5)

#提取 nan 值的布尔掩码
pd.isna(df1)

#平均值,一般情况下NaN会被忽略
df1.mean(),df1.mean(1)

#相减运算
df1.sub(df1*0.1,axis = 'index')

#apply函数
df1.apply(lambda x: x.max() - x.min())

#直方图
s = pd.DataFrame(np.random.randint(0,7,(2,10)))
s.loc[0].value_counts()

#字符串
s = pd.Series(['A', 'B', 'C', 'Aaba', 'Baca', np.nan, 'CABA', 'dog', 'cat'])
print(s.str.lower())

#合并
pd.concat([df1["A"],df1['D']])
pd.concat([df1.loc[dates[0]],df1.loc[dates[2]]])

#连接
left = pd.DataFrame({'key': ['foo', 'foo'], 'lval': [1, 2]})
right = pd.DataFrame({'key': ['foo', 'bar'], 'rval': [4, 5]})
pd.merge(left,right,on = 'key')