pandas用法大全

一、生成資料表 

1、首先匯入pandas庫，一般都會用到numpy庫，所以我們先導入備用：

import numpy as np

import pandas as pd

df = pd.dataframe(pd.read_csv('name.csv',header=1))

df = pd.dataframe(pd.read_excel('name.xlsx'))

df = pd.dataframe(,

columns =['id','date','city','category','age','price'])

df.shape

df.info()

df.dtypes

df['b'].dtype

df.isnull()

df.isnull()

df['b'].unique()

df.columns

df.head() #預設前10行資料

df.tail()    #預設後10 行資料

df.fillna(value=0)

df['prince'].fillna(df['prince'].mean())

df['city']=df['city'].map(str.strip)

df['city']=df['city'].str.lower()

df['price'].astype('int')

df.rename(columns=)

df['city'].drop_duplicates()

df['city'].drop_duplicates(keep='last')

df['city'].replace('sh', 'shanghai')

df1=pd.dataframe()

df_inner=pd.merge(df,df1,how='inner')  # 匹配合併，交集

df_left=pd.merge(df,df1,how='left')        #
df_right=pd.merge(df,df1,how='right')
df_outer=pd.merge(df,df1,how='outer')  #並集

df_inner.set_index('id')

df_inner.sort_values(by=['age'])

df_inner.sort_index()

df_inner['group'] = np.where(df_inner['price'] > 3000,'high','low')

df_inner.loc[(df_inner['city'] == 'beijing') & (df_inner['price'] >= 4000), 'sign']=1

pd.dataframe((x.split('-') for x in df_inner['category']),index=df_inner.index,columns=['category','size']))

df_inner=pd.merge(df_inner,split,right_index=true, left_index=true)

df_inner.loc[3]

df_inner.iloc[0:5]

df_inner.reset_index()

df_inner=df_inner.set_index('date')

df_inner[:'2013-01-04']

df_inner.iloc[:3,:2] #冒號前後的數字不再是索引的標籤名稱，而是資料所在的位置，從0開始，前三行，前兩列。

df_inner.iloc[[0,2,5],[4,5]] #提取第0、2、5行，4、5列

df_inner.ix[:'2013-01-03',:4] #2013-01-03號之前，前四列資料

df_inner['city'].isin(['beijing'])

df_inner.loc[df_inner['city'].isin(['beijing','shanghai'])]

pd.dataframe(category.str[:3])

df_inner.loc[(df_inner['age'] > 25) & (df_inner['city'] == 'beijing'), ['id','city','age','category','gender']]

df_inner.loc[(df_inner['age'] > 25) | (df_inner['city'] == 'beijing'), ['id','city','age','category','gender']].sort(['age'])

df_inner.loc[(df_inner['city'] != 'beijing'), ['id','city','age','category','gender']].sort(['id'])

df_inner.loc[(df_inner['city'] != 'beijing'), ['id','city','age','category','gender']].sort(['id']).city.count()

df_inner.query('city == ["beijing", "shanghai"]')

df_inner.query('city == ["beijing", "shanghai"]').price.sum()

df_inner.groupby('city').count()

df_inner.groupby('city')['id'].count()

df_inner.groupby(['city','size'])['id'].count()

df_inner.groupby('city')['price'].agg([len,np.sum, np.mean])

df_inner.sample(n=3)

weights = [0, 0, 0, 0, 0.5, 0.5]

df_inner.sample(n=2, weights=weights)

df_inner.sample(n=6, replace=false)

df_inner.sample(n=6, replace=true)

df_inner.describe().round(2).t #round函式設定顯示小數字，t表示轉置

df_inner['price'].std()

df_inner['price'].cov(df_inner['m-point'])

df_inner.cov()

df_inner['price'].corr(df_inner['m-point']) #相關係數在-1到1之間，接近1為正相關，接近-1為負相關，0為不相關

df_inner.corr()

df_inner.to_excel('excel_to_python.xlsx', sheet_name='bluewhale_cc')

df_inner.to_csv('excel_to_python.csv')

pandas用法大全

import numpy as np import pandas as pddf pd.dataframe pd.read csv name.csv header 1 df pd.dataframe pd.read excel name.xlsx df pd.dataframe columns id...

pandas用法大全

import numpy as np import pandas as pddf pd.dataframe pd.read csv name.csv header 1 df pd.dataframe pd.read excel name.xlsx df pd.dataframe columns id...

pandas 用法大全

import numpy as np import pandas as pddf pd.dataframe pd.read csv name.csv header 1 df pd.dataframe pd.read excel name.xlsx df pd.dataframe columns id...