Home > Notes > Python Pandas

pandas Operations part1

pandas Operations part1

pandas Operations part1

Below ate the pandas opertaion 1 Example.

 import numpy as np
 import pandas as pd
 df = pd.read_csv('/content/first_test.csv')
 #print(df)
 #df.info()
 #print(df[["id","name"]])
 #print(df.groupby(by=["zip"]).size())
 #print(df["id"].sum())
 #print(df["id"].count())
 #print(df["id"].max())
 #print(df["id"].min())
 #df["id"].mean()
 #df.groupby('zip')['id'].sum()
 #print(df[df.id==1])
 #print(df[(df.id == 1) & (df.zip == 560098)])
 #print(df[(df.id == 1) | (df.zip == 560098)])
 '''for index, row in df.iterrows():
    print(row["id"],",",row["name"])'''
 #arr = df["zip"].unique()
 #print(arr)
 #df.head()
 df.describe()

pandas Operations part1

Below ate the pandas opertaion 1 Example.

import numpy as np
 import pandas as pd
 df = pd.read_csv('/content/first_test.csv')
 from pandasql import sqldf
 output = sqldf("select * from df")
 output

drop

The drop() method removes the specified row or column. By specifying the column axis (axis='columns'), the drop() method removes the specified column. By specifying the row axis (axis='index'), the drop() method removes the specified row.

 df1 = pd.read_csv('/content/first_test.csv')
 df1.drop(['id', 'area'],1,inplace=True)
 print(df1)
 #pd.concat([df1,df2])

sort_values()

The sort_values() method sorts the DataFrame by the specified label.

 #res1 = df1.sort_values(by=['zip'], ascending=True)
 res2 = df1.sort_values(by=['zip'], ascending=False)
 print(res2)

rename

using rename we can rename From Source to column name.

df1.rename(columns = {'id':'id1', 'area':'area2'}, inplace = True)
 df1