Bring your Excel sheets into Python w/ Pandas!

!pip install pandas

import pandas as pd

df = pd.read_excel("SampleData.xlsx")

!pip install xlrd

df = pd.read_excel("SampleData.xlsx",sheet_name="SalesOrders") df

df.describe()

df = df.sort_values("Total") df

df = df.drop_duplicates() df

df.drop_duplicates(subset = ['Rep'],keep='first')

df['new_total'] = df["Units"] * df["Unit Cost"] df

df.groupby(["Rep"])

aggregate = df.groupby(["Rep"]).sum() aggregate

aggregate.sort_values("Total")

aggregate[aggregate["Total"] > 2000]

aggregate["Total"] > 2000

df.pivot_table(index=['Rep'], aggfunc=sum)

df

df.iloc[1,2] = None # this selects the second row and third column. Python is 0 indexed! df.iloc[3,:] = None # this sets the whole 4th row to Null df

df.isna().sum()

df.fillna(method="ffill")

df.fillna(0)

!pip install openpyxl==3.0.5

df.to_excel("newdata.xlsx") #save the data in excel format