import pandas as pd

retail=pd.read_csv("Retail_Transaction_Dataset.csv")

retail.columns = retail.columns.str.strip()

retail["TransactionDate"] = pd.to_datetime(retail["TransactionDate"], errors="coerce")

for column in ["Price", "Quantity", "TotalAmount", "DiscountApplied(%)"]:
    retail[column] = pd.to_numeric(retail[column], errors="coerce")

retail.head()

retail.dtypes

retail.shape

retail.describe()

retail.isnull().sum()

retail["ProductCategory"].unique()

retail.nunique()

retail['PaymentMethod'].unique()

retail[retail.duplicated()].shape[0]

retail['ProductCategory'].value_counts().rename_axis('ProductCategory').reset_index(name='count')

retail[retail['PaymentMethod']=='Credit Card'].shape[0]

retail[retail['ProductCategory']=='Electronics']['Price'].mean()

retail.groupby('ProductCategory')['Price'].mean()

Quantity = retail.groupby("ProductCategory")["Quantity"].sum().reset_index()

Quantity

retail.groupby("ProductCategory")["TotalAmount"].sum()

retail[(retail["PaymentMethod"] == "Cash") & (retail["TotalAmount"] > 60)]

retail["DiscountAmount"] = (retail["Price"]) * retail["DiscountApplied(%)"] / 100

retail.head()

retail["EffectivePrice"] = retail["Price"] - retail["DiscountAmount"]

retail

retail["Revenue"] = retail["EffectivePrice"] * retail["Quantity"]

retail["TransactionDay"] = retail["TransactionDate"].dt.day_name()

retail

retail.groupby("TransactionDay")["Revenue"].sum()
