import pandas as pd

from matplotlib import pyplot as plt

from scipy import stats

from scipy.stats import skew, kurtosis

df = pd.read_csv("Retail_Data.csv")

df.columns = df.columns.str.strip()

for column in ["Perindex", "Growth", "Retailer_Age"]:
    if column in df.columns:
        df[column] = pd.to_numeric(df[column], errors="coerce")

df.head()

df.info()

df.shape

df.describe(include = 'all')

plt.figure(figsize = (5, 4))

plt.boxplot(df['Perindex'].dropna())

plt.title('Box Plot(Performance Index)')

plt.ylabel('Perindex')

plt.xlabel('Retail observations')

plt.show()

plt.figure(figsize = (5, 4))

plt.boxplot(df['Growth'].dropna())

plt.title('Box Plot(Annual SalesGrowth)')

plt.ylabel('Growth')

plt.xlabel('Retail observations')

plt.show()
