Correlation Analysis

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt

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

# Pearson correlation coefficient (-1 to +1)
# +1 = perfect positive, 0 = no relation, -1 = perfect negative
corr_matrix = df.select_dtypes("number").corr()
print(corr_matrix)

# Correlation with one specific column
target_corr = corr_matrix["Sales"].sort_values(ascending=False)
print(target_corr)
# Sales         1.000000  ← self
# Marketing     0.842100  ← strong positive
# Store_Size    0.614300  ← moderate positive
# Returns      -0.421000  ← moderate negative
# Price        -0.023000  ← near zero (no relation)

# Visualise
plt.figure(figsize=(8, 6))
sns.heatmap(corr_matrix, annot=True, fmt=".2f",
            cmap="RdYlGn", center=0, vmin=-1, vmax=1)
plt.title("Correlation Matrix")
plt.tight_layout()
plt.show()

# Scatter plot for two correlated variables
sns.scatterplot(data=df, x="Marketing", y="Sales", alpha=0.6)
plt.title("Marketing Spend vs Sales")
plt.show()