├── Candy_Distubutor_analysis.py
└── README.md


/Candy_Distubutor_analysis.py:
--------------------------------------------------------------------------------
 1 | import numpy as np
 2 | import pandas as pd
 3 | import matplotlib.pyplot as plt
 4 | import seaborn as sns
 5 | 
 6 | df = pd.read_csv("C:\\Users\\hp\\OneDrive\\Desktop\\hari excel\\Candy_Sales.csv")
 7 | print(df)
 8 | print(df.head(10))
 9 | print(df.tail(10))
10 | print(df.info())
11 | print(df.describe())
12 | #1. Line Chart – Sales Over Time
13 | df['Month'] = df['Order Date'].dt.to_period('M')
14 | sales_by_month = df.groupby('Month')['Sales'].sum().reset_index()
15 | plt.figure(figsize=(12, 6))
16 | plt.plot(sales_by_month['Month'].astype(str), sales_by_month['Sales'], color='g', marker='d', linewidth=2)
17 | plt.title("Sales Over Time (Monthly)")
18 | plt.xlabel("Month")
19 | plt.ylabel("Total Sales")
20 | plt.xticks(rotation=90)
21 | plt.grid(True)
22 | #2.Bar Chart – Total Sales by Region
23 | sales_by_region = df.groupby('Region')['Sales'].sum().sort_values(ascending=False)
24 | plt.figure(figsize=(10, 6))
25 | sns.barplot(x=sales_by_region.values, y=sales_by_region.index, palette="viridis")
26 | plt.title("Total Sales by Region")
27 | plt.xlabel("Sales")
28 | plt.ylabel("Region")
29 | #3.Column Chart – Top 10 States by Units Sold
30 | units_by_state = df.groupby('State/Province')['Units'].sum().sort_values(ascending=False).head(10)
31 | plt.figure(figsize=(10, 6))
32 | sns.barplot(x=units_by_state.values, y=units_by_state.index, palette="magma")
33 | plt.title("Top 10 States by Units Sold")
34 | plt.xlabel("Units Sold")
35 | plt.ylabel("State")
36 | #4.Scatter Plot – Sales vs Gross Profit
37 | plt.figure(figsize=(8, 6))
38 | sns.scatterplot(data=df, x='Sales', y='Gross Profit', color="r")
39 | plt.title("Sales vs Gross Profit")
40 | plt.xlabel("Sales")
41 | plt.ylabel("Gross Profit")
42 | plt.grid(True)
43 | #5.Boxplot – Outliers Detection
44 | plt.figure(figsize=(8, 6))
45 | sns.boxplot(data=df, y='Sales', color='skyblue')
46 | plt.title("Boxplot - Sales")
47 | #6.Heatmap – Correlation Matrix
48 | corr = df[['Sales', 'Units', 'Gross Profit', 'Cost']].corr()
49 | plt.figure(figsize=(8, 6))
50 | sns.heatmap(corr, annot=True, cmap='Blues', fmt='.2f', linewidths=0.5)
51 | plt.title("Correlation Heatmap")
52 | #7.Pair Plot – Numerical Feature Relationships
53 | sns.pairplot(df[['Sales', 'Units', 'Gross Profit', 'Cost']], kind='scatter', diag_kind='hist', corner=True)
54 | plt.suptitle("Pair Plot of Numerical Features", y=1.02)
55 | 
56 | plt.show()
57 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # python_project


--------------------------------------------------------------------------------