#Pandas ''' 1,Pandas是Python的一个数据分析报包，该工具为解决数据分析任务而创建。 2，Pandas纳入大量库和标准数据模型，提供搞笑的操作数据集所需的工具 3.pandas提供大量能使我们快速便捷地处理数据的1函数方法 4，Pandas是字典形式，基于Numpy创建，让Numpy为中心的应用变得更加简单 ''' import pandas as pd import numpy as np #4 Pandas 数据结构 #4.1Series
s = pd.Series([1,2,3,np.nan,5,6])#索引在左边值在右边
print(s)
#4.2 Date Frame #DateFrame是表格型数据结构，包含一组有序的列，每列可以使不同的值类型。DateFrame有行索引和列索引，可以看成由Series组成的字典。
dates = pd.date_range('20180310',periods = 6)
df = pd.DataFrame(np.random.rand(6,4),index=dates,columns=['A','B','C','D'])
print(df)
print(df['B'])
#创建特定数据的DataFrame
df_1 = pd.DataFrame({
'A':1.,
'B':pd.date_range('20180923',periods=4),
'D':np.array([2]*4,dtype='int32'),
'E':pd.Categorical(['test','train','test','train']),
'F':'foo'
})
print(df_1)
print(df_1.dtypes)
print(df_1.index)#行的序号
print(df_1.columns)#列的序号
print(df_1.values)#把每个值进行打印
print(df_1.describe())#数字总结
print(df_1.T)#数字反转
print(df_1.sort_index(axis=1,ascending=False))#axis等于按第一列排序，如ABCDEFG，然后ascending倒序进行显示
print(df_1.sort_values(by='E'))#按值进行排列
#pandas选择数据
dates = pd.date_range('20180924',periods=6)
df = pd.DataFrame(np.random.rand(6,4),index=dates,columns=['A','B','C','D'])
print(df)
print(df[0:3],df['20180910':'20180926'])#第一次切片选择，第二次按照筛选条件选择
print(df.loc['20180924',['A','B']])#按照行标签进行选择
print(df.iloc[3,1])#输出第三行第一列的数据
print(df.iloc[3:5,0:2])#3,5行，0,3列
print(df.iloc[[1,2,4],[0,2]])#不连续筛选
print(df[df.A > 0])#筛选出df.A大于0的元素
#pandas设置数据
datas = pd.date_range('20180310',periods=6)
df = pd.DataFrame(np.arange(24).reshape(6,4),index=datas,columns=['A','B','C','D'])
print(df)
df.iloc[2,2] = 999
df.loc['2018-03-15','D'] = 999
print(df)
df[df.A > 0] = 999#A列大于0的为999???
print(df)
df['F'] = np.NAN
print(df)
df['E'] = pd.Series([1,2,3,4,5,6],index=pd.date_range('20180310',periods=6))#添加一列
print(df)
#7Pandas处理数据
dates = pd.date_range('20180310',periods=6)
df = pd.DataFrame(np.arange(24).reshape(6,4),index=dates,columns=['A','B','C','D'])
df.iloc[0,1]=np.nan
df.iloc[1,2]=np.nan
print(df)
# print(df.dropna(axis=0,how='any'))#0对行进行操作 1对列进行操作 any：只要存在NaN即可drop掉 all:必须全部是NaN才可drop
# print(df.fillna(value=0))#将NaN值替换为0
print(pd.isnull(df))#是nan为true不是nan为false
print(np.any(df.isnull()))#判断数据中是否存在nanz值
#8 pandas的导入导出
data = pd.read_csv('test1.csv')
data.to_pickle('test.pickle')#将资料存取成pickle文件
#9.pandas合并数据
df1 = pd.DataFrame(np.ones((3,4))*0,columns=['a','b','c','d'])
df2 = pd.DataFrame(np.ones((3,4))*1,columns=['a','b','c','d'])
df3 = pd.DataFrame(np.ones((3,4))*2,columns=['a','b','c','d'])
res = pd.concat([df1,df2,df3],axis=0,ignore_index=True)#0表示行合并，1表示列合并，ingnore_index重置序列index index变为1-8
print(res)
#join合并
df1 = pd.DataFrame(np.ones((3,4))*0,columns=['a','b','c','d'],index=[1,2,3])
df2 = pd.DataFrame(np.ones((3,4))*1,columns=['a','b','c','d'],index=[2,3,4])
print(df1)
print(df2)
# res = pd.concat([df1,df2],axis=1,join='outer')#行往外合并
# print(res)
res = pd.concat([df1,df2],axis=1,join_axes=[df1.index])#以df1的序列进行合并，df2中没有的序列NAN值填充
print(res)
#append添加
df1 = pd.DataFrame(np.ones((3,4))*0,columns=['a','b','c','d'])
df2 = pd.DataFrame(np.ones((3,4))*1,columns=['a','b','c','d'])
df3 = pd.DataFrame(np.ones((3,4))*2,columns=['a','b','c','d'])
s1 = pd.Series([1,2,3,4],index=['a','b','c','d'])
res = df1.append(df2,ignore_index=True)#将df2合并到df1下面并重置index
print(res)
res = df1.append(s1,ignore_index=True)#将s1合并到df1下面并重置index
print(res)
#pandas和并merge
#依据一组key合并
left = pd.DataFrame({
'key':['k1','k2','k3','k4'],
'A':['A1','A2','A3','A4'],
'B':['B1','B2','B3','B4']
})
print(left)
right = pd.DataFrame({
'key':['k1','k2','k3','k4'],
'C':['C1','C2','C3','C4'],
'D':['D1','D2','D3','D4']
})
print(right)
res = pd.merge(left,right,on = 'key')
print(res)
#依据两组key合并
left = pd.DataFrame({
'key':['k0','k0','k1','k2'],
'key2':['k0','k1','k0','k1'],
'A':['A1','A2','A3','A4'],
'B':['B1','B2','B3','B4']
})
right = pd.DataFrame({
'key':['k0','k1','k1','k2'],
'key2':['k0','k0','k0','k0'],
'C':['C1','C2','C3','C4'],
'D':['D1','D2','D3','D4']
})
print(left)
print(right)
res = pd.merge(left,right,on=['key','key2'],how='inner')#how = outer left right
print(res)
#indicator合并
df1 = pd.DataFrame({'col1':[0,1],'col_left':['a','b']}) df2 = pd.DataFrame({'col1':[1,2,2],'col_right':[2,2,2]}) print(df1) print(df2)
res = pd.merge(df1,df2,on='col1',how='outer',indicator=True)#依据col1进行合并 并启用indicator = True输出没想合并式
print(res)
res = pd.merge(df1,df2,on='col1',how='outer',indicator='indicator_column')#自定义indicator column名称 print(res)
