Wednesday, 20 December 2023

DataFrame Summary with Functions

 DataFrame Summary with Functions

import pandas as pd

pd.set_option('display.max_columns', None)

pd.set_option('display.max_rows', None)

df = pd.read_excel("D:\\1.xlsx", "SheetName", index_col='Index_Column_rowlabel', usecols='B:AG',skiprows=2)  

df.loc['No_of_Cats':'No_of_Dogs',:]

df = df.drop('Animals', axis=1)

df=df.reset_index()

df.loc[(df['Index_Column_rowlabel']=='No_of_Cats') | (df['Index_Column_rowlabel']=='No_of_Dogs')]

df=df.rename(columns={"Mobile Voice":"Date_T"})

df=df.transpose() 

df.columns = df.iloc[0]

df

####################

import pandas as pd

pd.set_option('display.max_columns', None)

pd.set_option('display.max_rows', None)

df = pd.read_excel("D:\\1.xlsx", "sheetname",index_col='Movekp' usecols='B:AGG',skiprows=2)  

#get the/quering the specific information from the sheet using loc function of the pandas

newdf=df.loc[(df['Movekp']=='Sub in Ind') | (df['Movekp']=='Sub in Pk')]

newdf

#droping the column

newdf=newdf.drop('Venture', axis=1)

#rename the columns

newdf=newdf.rename(columns={'Move`':'Date'})

#take transpose of the dataframe

newdf=newdf.transpose()

newdf=newdf.reset_index()

#assigning the value of first row to columns

newdf.columns = newdf.iloc[0]

# remove first row

newdf=newdf.tail(-1)

#save to disk

newdf.to_csv("D:\\1_data.csv")

# Information about df

newdf.info()

#importing datetime library.

from datetime import date,datetime

# converting Date column to datetime type

newdf["Date"]=pd.to_datetime(newdf["Date"])

# set the date column as index of dataframe df

newdf=newdf.set_index('Date')

# plot the graph of the dataframe df that is line

newdf.plot()

Selection under condition in data frame ,along with Group by clause in Pandas dataframe

import pandas

df=pandas.read_csv(".//abc.csv")

df['date_t']=df.ds.astype(dtype='datetime64[ms]')

df['month'] = df['date_t'].dt.month

df['year'] = df['date_t'].dt.year

df.info()

df_tmp = df.groupby(['date_t','month','year'])['yhat'].sum().reset_index().sort_values( 'yhat',ascending = False)

r=df_tmp[((df_tmp['month'] == 1)|(df_tmp['month'] == 2)) & (df_tmp['year'] == 2002)].groupby(['month','year'])['yhat'].apply(lambda grp: grp.nlargest(3).mean())

r.to_csv('./Average_of_t3.csv')


No comments:

Post a Comment