├── 1.py
└── code.ipynb


/1.py:
--------------------------------------------------------------------------------
  1 | import pandas as pd
  2 | import numpy as np
  3 | import matplotlib.pyplot as plt
  4 | import seaborn as sns
  5 | 
  6 | # Load your dataset
  7 | df = pd.read_csv("/Users/abhaykumargupta/Desktop/pythonCA2/Warehouse_and_Retail_Sales.csv")
  8 | 
  9 | # Basic information
 10 | print(" Dataset Overview")
 11 | print(df.info())
 12 | print("/n First 5 Rows")
 13 | print(df.head())
 14 | 
 15 | # Create Date column
 16 | df['Date'] = pd.to_datetime(dict(year=df['YEAR'], month=df['MONTH'], day=1))
 17 | 
 18 | # Create Total Sales column
 19 | df['Total Sales'] = df['RETAIL SALES'] + df['WAREHOUSE SALES']
 20 | 
 21 | # Check missing values
 22 | print("/n Missing Values:")
 23 | print(df.isnull().sum())
 24 | 
 25 | # Check for duplicates
 26 | print("/n Duplicate Records:", df.duplicated().sum())
 27 | 
 28 | # Drop duplicates
 29 | df.drop_duplicates(inplace=True)
 30 | 
 31 | # Summary statistics
 32 | print("/n Summary Statistics:")
 33 | print(df.describe())
 34 | 
 35 | # Unique product and category info
 36 | print("/n Unique Products:", df['ITEM DESCRIPTION'].nunique())
 37 | print(" Item Types:", df['ITEM TYPE'].unique())
 38 | 
 39 | # Visualization 1: Distribution of Total Sales
 40 | plt.figure(figsize=(10, 5))
 41 | sns.histplot(df['Total Sales'], bins=50, kde=True, color='skyblue')
 42 | plt.title("Distribution of Total Sales")
 43 | plt.xlabel("Total Sales ($)")
 44 | plt.ylabel("Frequency")
 45 | plt.tight_layout()
 46 | plt.show()
 47 | 
 48 | # Visualization 2: Total Sales by Item Type
 49 | plt.figure(figsize=(10, 5))
 50 | sns.barplot(
 51 |     data=df,
 52 |     x='ITEM TYPE',
 53 |     y='Total Sales',
 54 |     estimator=sum,
 55 |     hue='ITEM TYPE',
 56 |     palette='viridis',
 57 |     legend=False,
 58 |     errorbar=None
 59 | )
 60 | plt.title("Total Sales by Item Type")
 61 | plt.xlabel("Item Type")
 62 | plt.ylabel("Total Sales ($)")
 63 | plt.xticks(rotation=45)
 64 | plt.tight_layout()
 65 | plt.show()
 66 | 
 67 | 
 68 | # Basic information
 69 | print(" Dataset Overview")
 70 | print(df.info())
 71 | print("\n First 5 Rows")
 72 | print(df.head())
 73 | 
 74 | # Create Date column
 75 | df['Date'] = pd.to_datetime(dict(year=df['YEAR'], month=df['MONTH'], day=1))
 76 | 
 77 | # Create Total Sales column
 78 | df['Total Sales'] = df['RETAIL SALES'] + df['WAREHOUSE SALES']
 79 | 
 80 | # Check missing values
 81 | print("\n Missing Values:")
 82 | print(df.isnull().sum())
 83 | 
 84 | # Check for duplicates
 85 | print("\n Duplicate Records:", df.duplicated().sum())
 86 | 
 87 | # Drop duplicates
 88 | df.drop_duplicates(inplace=True)
 89 | 
 90 | # Summary statistics
 91 | print("\n Summary Statistics:")
 92 | print(df.describe())
 93 | 
 94 | # Unique product and category info
 95 | print("\n Unique Products:", df['ITEM DESCRIPTION'].nunique())
 96 | print(" Item Types:", df['ITEM TYPE'].unique())
 97 | 
 98 | # Visualization 1: Distribution of Total Sales
 99 | plt.figure(figsize=(10, 5))
100 | sns.histplot(df['Total Sales'], bins=50, kde=True, color='skyblue')
101 | plt.title("Distribution of Total Sales")
102 | plt.xlabel("Total Sales ($)")
103 | plt.ylabel("Frequency")
104 | plt.tight_layout()
105 | plt.show()
106 | # Visualization 2: Total Sales by Item Type
107 | plt.figure(figsize=(10, 5))
108 | sns.barplot(
109 |     data=df,
110 |     x='ITEM TYPE',
111 |     y='Total Sales',
112 |     estimator=sum,
113 |     hue='ITEM TYPE',
114 |     palette='viridis',
115 |     legend=False,
116 |     errorbar=None
117 | )
118 | plt.title("Total Sales by Item Type")
119 | plt.xlabel("Item Type")
120 | plt.ylabel("Total Sales ($)")
121 | plt.xticks(rotation=45)
122 | plt.tight_layout()
123 | plt.show()
124 | 
125 | 
126 | # Create Date column
127 | df['Date'] = pd.to_datetime(dict(year=df['YEAR'], month=df['MONTH'], day=1))
128 | 
129 | # Create Total Sales column
130 | df['Total Sales'] = df['RETAIL SALES'] + df['WAREHOUSE SALES']
131 | 
132 | # Check missing values
133 | print("\n Missing Values:")
134 | print(df.isnull().sum())
135 | 
136 | # Check for duplicates
137 | print("\n Duplicate Records:", df.duplicated().sum())
138 | 
139 | # Drop duplicates
140 | df.drop_duplicates(inplace=True)
141 | 
142 | # Summary statistics
143 | print("\n Summary Statistics:")
144 | print(df.describe())
145 | 
146 | # Unique product and category info
147 | print("\n Unique Products:", df['ITEM DESCRIPTION'].nunique())
148 | print(" Item Types:", df['ITEM TYPE'].unique())
149 | 
150 | # Visualization 1: Distribution of Total Sales
151 | plt.figure(figsize=(10, 5))
152 | sns.histplot(df['Total Sales'], bins=50, kde=True, color='skyblue')
153 | plt.title("Distribution of Total Sales")
154 | plt.xlabel("Total Sales ($)")
155 | plt.ylabel("Frequency")
156 | plt.tight_layout()
157 | plt.show()
158 | 
159 | # Visualization 2: Total Sales by Item Type
160 | plt.figure(figsize=(10, 5))
161 | sns.barplot(
162 |     data=df,
163 |     x='ITEM TYPE',
164 |     y='Total Sales',
165 |     estimator=sum,
166 |     hue='ITEM TYPE',
167 |     palette='viridis',
168 |     legend=False,
169 |     errorbar=None
170 | )
171 | plt.title("Total Sales by Item Type")
172 | plt.xlabel("Item Type")
173 | plt.ylabel("Total Sales ($)")
174 | plt.xticks(rotation=45)
175 | plt.tight_layout()
176 | plt.show()
177 | 
178 | # Objective 1: Sales Trend Analysis Over Time
179 | #  Create a proper datetime column from YEAR and MONTH
180 | df['Date'] = pd.to_datetime(dict(year=df['YEAR'], month=df['MONTH'], day=1))
181 | 
182 | #  Calculate Total Sales
183 | df['Total Sales'] = df['RETAIL SALES'] + df['WAREHOUSE SALES']
184 | 
185 | #  Group by Date (monthly)
186 | monthly_sales = df.groupby('Date')['Total Sales'].sum().reset_index()
187 | 
188 | #  Group by Year
189 | yearly_sales = df.groupby('YEAR')['Total Sales'].sum().reset_index()
190 | 
191 | #  Group by Quarter
192 | df['Quarter'] = df['Date'].dt.to_period('Q')
193 | quarterly_sales = df.groupby('Quarter')['Total Sales'].sum().reset_index()
194 | quarterly_sales['Quarter'] = quarterly_sales['Quarter'].astype(str)  # Convert Period to string
195 | 
196 | #  Plot Monthly Sales Trend
197 | plt.figure(figsize=(12, 6))
198 | sns.lineplot(data=monthly_sales, x='Date', y='Total Sales', marker='o', color='steelblue')
199 | plt.title("Monthly Sales Trend")
200 | plt.xlabel("Date")
201 | plt.ylabel("Total Sales ($)")
202 | plt.grid(True)
203 | plt.tight_layout()
204 | plt.show()
205 | 
206 | #  Plot Yearly Sales Summary
207 | plt.figure(figsize=(8, 5))
208 | sns.barplot(
209 |     data=yearly_sales,
210 |     x='YEAR',
211 |     y='Total Sales',
212 |     hue='YEAR',             
213 |     palette='crest',
214 |     legend=False,
215 |     errorbar=None           
216 | )
217 | plt.title("Yearly Total Sales")  
218 | 
219 | plt.ylabel("Total Sales ($)")
220 | plt.tight_layout()
221 | plt.show()
222 | 
223 | # Plot Quarterly Sales Trend
224 | plt.figure(figsize=(10, 5))
225 | sns.lineplot(data=quarterly_sales, x='Quarter', y='Total Sales', marker='o', color='green')
226 | plt.title("Quarterly Sales Trend")
227 | plt.xlabel("Quarter")
228 | plt.ylabel("Total Sales ($)")
229 | plt.xticks(rotation=45)
230 | plt.tight_layout()
231 | plt.show()
232 | 
233 | # Objective 2: Comparison Between Warehouse and Retail Sales
234 | # Create Total Sales column if not already present
235 | df['Total Sales'] = df['RETAIL SALES'] + df['WAREHOUSE SALES']
236 | 
237 | # Create a long-form DataFrame for Retail vs Warehouse
238 | sales_by_type = pd.melt(
239 |     df,
240 |     id_vars=['Date'] if 'Date' in df.columns else None,
241 |     value_vars=['RETAIL SALES', 'WAREHOUSE SALES'],
242 |     var_name='Sales Channel',
243 |     value_name='Sales'
244 | )
245 | 
246 | # Clean channel names
247 | sales_by_type['Sales Channel'] = sales_by_type['Sales Channel'].str.replace(' SALES', '')
248 | 
249 | # Total and average sales by channel
250 | channel_summary = sales_by_type.groupby('Sales Channel')['Sales'].agg(['sum', 'mean']).reset_index()
251 | print("Sales Summary (Total & Average):")
252 | print(channel_summary)
253 | 
254 | # Bar Plot: Total Sales by Channel
255 | plt.figure(figsize=(6, 5))
256 | sns.barplot(
257 |     data=channel_summary,
258 |     x='Sales Channel',
259 |     y='sum',
260 |     hue='Sales Channel',
261 |     palette='Set2',
262 |     legend=False,
263 |     errorbar=None
264 | )
265 | plt.title("Total Sales by Channel")
266 | plt.ylabel("Total Sales ($)")
267 | plt.tight_layout()
268 | plt.show()
269 | 
270 | 
271 | # Pie Chart: Contribution of Each Channel
272 | plt.figure(figsize=(6, 6))
273 | plt.pie(
274 |     channel_summary['sum'],
275 |     labels=channel_summary['Sales Channel'],
276 |     autopct='%1.1f%%',
277 |     colors=sns.color_palette('Set2')
278 | )
279 | plt.title("Sales Contribution: Retail vs Warehouse")
280 | plt.tight_layout()
281 | plt.show()
282 | 
283 | # Objective 3: Top Performing Products
284 | 
285 | # Create Total Sales column (if not already added)
286 | df['Total Sales'] = df['RETAIL SALES'] + df['WAREHOUSE SALES']
287 | 
288 | # 1️⃣ Top Products by Total Sales
289 | top_products_total = df.groupby('ITEM TYPE')['Total Sales'].sum().sort_values(ascending=False).head(10).reset_index()
290 | 
291 | # 2️⃣ Top Products by Retail Sales
292 | top_products_retail = df.groupby('ITEM TYPE')['RETAIL SALES'].sum().sort_values(ascending=False).head(10).reset_index()
293 | 
294 | # 3️⃣ Top Products by Warehouse Sales
295 | top_products_warehouse = df.groupby('ITEM TYPE')['WAREHOUSE SALES'].sum().sort_values(ascending=False).head(10).reset_index()
296 | 
297 | # 🔹 Horizontal Bar Plot for Top Products by Total Sales
298 | plt.figure(figsize=(10, 6))
299 | sns.barplot(
300 |     data=top_products_total,
301 |     y='ITEM TYPE',
302 |     x='Total Sales',
303 |     hue='ITEM TYPE',
304 |     palette='Blues_d',
305 |     legend=False,
306 |     errorbar=None  # remove confidence intervals
307 | )
308 | plt.title("Top 10 Products by Total Sales")
309 | plt.xlabel("Total Sales ($)")
310 | plt.ylabel("Product")
311 | plt.tight_layout()
312 | plt.show()
313 | 
314 | # 🔹 Horizontal Bar Plot for Top Products by Retail Sales
315 | plt.figure(figsize=(10, 6))
316 | sns.barplot(
317 |     data=top_products_retail,
318 |     y='ITEM TYPE',
319 |     x='RETAIL SALES',
320 |     hue='ITEM TYPE',
321 |     palette='Greens_d',
322 |     legend=False,
323 |     errorbar=None
324 | )
325 | plt.title("Top 10 Products by Retail Sales")
326 | plt.xlabel("Retail Sales ($)")
327 | plt.ylabel("Product")
328 | plt.tight_layout()
329 | plt.show()
330 | 
331 | # 🔹 Horizontal Bar Plot for Top Products by Warehouse Sales
332 | plt.figure(figsize=(10, 6))
333 | sns.barplot(
334 |     data=top_products_warehouse,
335 |     y='ITEM TYPE',
336 |     x='WAREHOUSE SALES',
337 |     hue='ITEM TYPE',
338 |     palette='Oranges_d',
339 |     legend=False,
340 |     errorbar=None
341 | )
342 | plt.title("Top 10 Products by Warehouse Sales")
343 | plt.xlabel("Warehouse Sales ($)")
344 | plt.ylabel("Product")
345 | plt.tight_layout()
346 | plt.show()
347 | 
348 | # Objective 4:  Correlation Between Product Price and Sales Volume
349 | 
350 | # Filter out rows with 0 transfers to avoid divide-by-zero
351 | df_valid = df[df['RETAIL TRANSFERS'] > 0].copy()
352 | 
353 | # Calculate approximate price per unit
354 | df_valid['PRICE PER UNIT'] = df_valid['RETAIL SALES'] / df_valid['RETAIL TRANSFERS']
355 | 
356 | # Display correlation
357 | correlation = df_valid[['PRICE PER UNIT', 'RETAIL TRANSFERS']].corr()
358 | print("🔗 Correlation Matrix:")
359 | print(correlation)
360 | 
361 | # Scatter plot with regression line
362 | plt.figure(figsize=(8, 6))
363 | sns.regplot(data=df_valid, x='PRICE PER UNIT', y='RETAIL TRANSFERS', scatter_kws={'alpha':0.5})
364 | plt.title("Correlation Between Product Price and Quantity Sold")
365 | plt.xlabel("Price Per Unit ($)")
366 | plt.ylabel("Quantity Sold (Retail Transfers)")
367 | plt.tight_layout()
368 | plt.show()
369 | 
370 | # Objective 5:  Peak Sales Months
371 | 
372 | # Create datetime column
373 | df['DATE'] = pd.to_datetime(df['YEAR'].astype(str) + '-' + df['MONTH'].astype(str) + '-01')
374 | 
375 | # Extract month name for visualization
376 | df['MONTH_NAME'] = df['DATE'].dt.strftime('%B')
377 | 
378 | # Calculate total sales
379 | df['TOTAL SALES'] = df['RETAIL SALES'] + df['WAREHOUSE SALES']
380 | 
381 | # Order the months
382 | month_order = ['January', 'February', 'March', 'April', 'May', 'June',
383 |                'July', 'August', 'September', 'October', 'November', 'December']
384 | 
385 | # Group and sort data
386 | monthly_sales = df.groupby('MONTH_NAME')['TOTAL SALES'].sum().reindex(month_order)
387 | 
388 | # Plot the result without emoji and FutureWarning
389 | plt.figure(figsize=(10, 6))
390 | sns.barplot(x=monthly_sales.index, y=monthly_sales.values)
391 | plt.xticks(rotation=45)
392 | plt.title("Total Sales by Month")  
393 | plt.xlabel("Month")
394 | plt.ylabel("Total Sales")
395 | plt.tight_layout()
396 | plt.show()
397 | 


--------------------------------------------------------------------------------
/code.ipynb:
--------------------------------------------------------------------------------
  1 | import pandas as pd
  2 | import numpy as np
  3 | import matplotlib.pyplot as plt
  4 | import seaborn as sns
  5 | 
  6 | # Load your dataset
  7 | df = pd.read_csv("/Users/abhaykumargupta/Desktop/pythonCA2/Warehouse_and_Retail_Sales.csv")
  8 | 
  9 | # Basic information
 10 | print(" Dataset Overview")
 11 | print(df.info())
 12 | print("/n First 5 Rows")
 13 | print(df.head())
 14 | 
 15 | # Create Date column
 16 | df['Date'] = pd.to_datetime(dict(year=df['YEAR'], month=df['MONTH'], day=1))
 17 | 
 18 | # Create Total Sales column
 19 | df['Total Sales'] = df['RETAIL SALES'] + df['WAREHOUSE SALES']
 20 | 
 21 | # Check missing values
 22 | print("/n Missing Values:")
 23 | print(df.isnull().sum())
 24 | 
 25 | # Check for duplicates
 26 | print("/n Duplicate Records:", df.duplicated().sum())
 27 | 
 28 | # Drop duplicates
 29 | df.drop_duplicates(inplace=True)
 30 | 
 31 | # Summary statistics
 32 | print("/n Summary Statistics:")
 33 | print(df.describe())
 34 | 
 35 | # Unique product and category info
 36 | print("/n Unique Products:", df['ITEM DESCRIPTION'].nunique())
 37 | print(" Item Types:", df['ITEM TYPE'].unique())
 38 | 
 39 | # Visualization 1: Distribution of Total Sales
 40 | plt.figure(figsize=(10, 5))
 41 | sns.histplot(df['Total Sales'], bins=50, kde=True, color='skyblue')
 42 | plt.title("Distribution of Total Sales")
 43 | plt.xlabel("Total Sales ($)")
 44 | plt.ylabel("Frequency")
 45 | plt.tight_layout()
 46 | plt.show()
 47 | 
 48 | # Visualization 2: Total Sales by Item Type
 49 | plt.figure(figsize=(10, 5))
 50 | sns.barplot(
 51 |     data=df,
 52 |     x='ITEM TYPE',
 53 |     y='Total Sales',
 54 |     estimator=sum,
 55 |     hue='ITEM TYPE',
 56 |     palette='viridis',
 57 |     legend=False,
 58 |     errorbar=None
 59 | )
 60 | plt.title("Total Sales by Item Type")
 61 | plt.xlabel("Item Type")
 62 | plt.ylabel("Total Sales ($)")
 63 | plt.xticks(rotation=45)
 64 | plt.tight_layout()
 65 | plt.show()
 66 | 
 67 | 
 68 | # Basic information
 69 | print(" Dataset Overview")
 70 | print(df.info())
 71 | print("\n First 5 Rows")
 72 | print(df.head())
 73 | 
 74 | # Create Date column
 75 | df['Date'] = pd.to_datetime(dict(year=df['YEAR'], month=df['MONTH'], day=1))
 76 | 
 77 | # Create Total Sales column
 78 | df['Total Sales'] = df['RETAIL SALES'] + df['WAREHOUSE SALES']
 79 | 
 80 | # Check missing values
 81 | print("\n Missing Values:")
 82 | print(df.isnull().sum())
 83 | 
 84 | # Check for duplicates
 85 | print("\n Duplicate Records:", df.duplicated().sum())
 86 | 
 87 | # Drop duplicates
 88 | df.drop_duplicates(inplace=True)
 89 | 
 90 | # Summary statistics
 91 | print("\n Summary Statistics:")
 92 | print(df.describe())
 93 | 
 94 | # Unique product and category info
 95 | print("\n Unique Products:", df['ITEM DESCRIPTION'].nunique())
 96 | print(" Item Types:", df['ITEM TYPE'].unique())
 97 | 
 98 | # Visualization 1: Distribution of Total Sales
 99 | plt.figure(figsize=(10, 5))
100 | sns.histplot(df['Total Sales'], bins=50, kde=True, color='skyblue')
101 | plt.title("Distribution of Total Sales")
102 | plt.xlabel("Total Sales ($)")
103 | plt.ylabel("Frequency")
104 | plt.tight_layout()
105 | plt.show()
106 | # Visualization 2: Total Sales by Item Type
107 | plt.figure(figsize=(10, 5))
108 | sns.barplot(
109 |     data=df,
110 |     x='ITEM TYPE',
111 |     y='Total Sales',
112 |     estimator=sum,
113 |     hue='ITEM TYPE',
114 |     palette='viridis',
115 |     legend=False,
116 |     errorbar=None
117 | )
118 | plt.title("Total Sales by Item Type")
119 | plt.xlabel("Item Type")
120 | plt.ylabel("Total Sales ($)")
121 | plt.xticks(rotation=45)
122 | plt.tight_layout()
123 | plt.show()
124 | 
125 | 
126 | # Create Date column
127 | df['Date'] = pd.to_datetime(dict(year=df['YEAR'], month=df['MONTH'], day=1))
128 | 
129 | # Create Total Sales column
130 | df['Total Sales'] = df['RETAIL SALES'] + df['WAREHOUSE SALES']
131 | 
132 | # Check missing values
133 | print("\n Missing Values:")
134 | print(df.isnull().sum())
135 | 
136 | # Check for duplicates
137 | print("\n Duplicate Records:", df.duplicated().sum())
138 | 
139 | # Drop duplicates
140 | df.drop_duplicates(inplace=True)
141 | 
142 | # Summary statistics
143 | print("\n Summary Statistics:")
144 | print(df.describe())
145 | 
146 | # Unique product and category info
147 | print("\n Unique Products:", df['ITEM DESCRIPTION'].nunique())
148 | print(" Item Types:", df['ITEM TYPE'].unique())
149 | 
150 | # Visualization 1: Distribution of Total Sales
151 | plt.figure(figsize=(10, 5))
152 | sns.histplot(df['Total Sales'], bins=50, kde=True, color='skyblue')
153 | plt.title("Distribution of Total Sales")
154 | plt.xlabel("Total Sales ($)")
155 | plt.ylabel("Frequency")
156 | plt.tight_layout()
157 | plt.show()
158 | 
159 | # Visualization 2: Total Sales by Item Type
160 | plt.figure(figsize=(10, 5))
161 | sns.barplot(
162 |     data=df,
163 |     x='ITEM TYPE',
164 |     y='Total Sales',
165 |     estimator=sum,
166 |     hue='ITEM TYPE',
167 |     palette='viridis',
168 |     legend=False,
169 |     errorbar=None
170 | )
171 | plt.title("Total Sales by Item Type")
172 | plt.xlabel("Item Type")
173 | plt.ylabel("Total Sales ($)")
174 | plt.xticks(rotation=45)
175 | plt.tight_layout()
176 | plt.show()
177 | 
178 | # Objective 1: Sales Trend Analysis Over Time
179 | #  Create a proper datetime column from YEAR and MONTH
180 | df['Date'] = pd.to_datetime(dict(year=df['YEAR'], month=df['MONTH'], day=1))
181 | 
182 | #  Calculate Total Sales
183 | df['Total Sales'] = df['RETAIL SALES'] + df['WAREHOUSE SALES']
184 | 
185 | #  Group by Date (monthly)
186 | monthly_sales = df.groupby('Date')['Total Sales'].sum().reset_index()
187 | 
188 | #  Group by Year
189 | yearly_sales = df.groupby('YEAR')['Total Sales'].sum().reset_index()
190 | 
191 | #  Group by Quarter
192 | df['Quarter'] = df['Date'].dt.to_period('Q')
193 | quarterly_sales = df.groupby('Quarter')['Total Sales'].sum().reset_index()
194 | quarterly_sales['Quarter'] = quarterly_sales['Quarter'].astype(str)  # Convert Period to string
195 | 
196 | #  Plot Monthly Sales Trend
197 | plt.figure(figsize=(12, 6))
198 | sns.lineplot(data=monthly_sales, x='Date', y='Total Sales', marker='o', color='steelblue')
199 | plt.title("Monthly Sales Trend")
200 | plt.xlabel("Date")
201 | plt.ylabel("Total Sales ($)")
202 | plt.grid(True)
203 | plt.tight_layout()
204 | plt.show()
205 | 
206 | #  Plot Yearly Sales Summary
207 | plt.figure(figsize=(8, 5))
208 | sns.barplot(
209 |     data=yearly_sales,
210 |     x='YEAR',
211 |     y='Total Sales',
212 |     hue='YEAR',             
213 |     palette='crest',
214 |     legend=False,
215 |     errorbar=None           
216 | )
217 | plt.title("Yearly Total Sales")  
218 | 
219 | plt.ylabel("Total Sales ($)")
220 | plt.tight_layout()
221 | plt.show()
222 | 
223 | # Plot Quarterly Sales Trend
224 | plt.figure(figsize=(10, 5))
225 | sns.lineplot(data=quarterly_sales, x='Quarter', y='Total Sales', marker='o', color='green')
226 | plt.title("Quarterly Sales Trend")
227 | plt.xlabel("Quarter")
228 | plt.ylabel("Total Sales ($)")
229 | plt.xticks(rotation=45)
230 | plt.tight_layout()
231 | plt.show()
232 | 
233 | # Objective 2: Comparison Between Warehouse and Retail Sales
234 | # Create Total Sales column if not already present
235 | df['Total Sales'] = df['RETAIL SALES'] + df['WAREHOUSE SALES']
236 | 
237 | # Create a long-form DataFrame for Retail vs Warehouse
238 | sales_by_type = pd.melt(
239 |     df,
240 |     id_vars=['Date'] if 'Date' in df.columns else None,
241 |     value_vars=['RETAIL SALES', 'WAREHOUSE SALES'],
242 |     var_name='Sales Channel',
243 |     value_name='Sales'
244 | )
245 | 
246 | # Clean channel names
247 | sales_by_type['Sales Channel'] = sales_by_type['Sales Channel'].str.replace(' SALES', '')
248 | 
249 | # Total and average sales by channel
250 | channel_summary = sales_by_type.groupby('Sales Channel')['Sales'].agg(['sum', 'mean']).reset_index()
251 | print("Sales Summary (Total & Average):")
252 | print(channel_summary)
253 | 
254 | # Bar Plot: Total Sales by Channel
255 | plt.figure(figsize=(6, 5))
256 | sns.barplot(
257 |     data=channel_summary,
258 |     x='Sales Channel',
259 |     y='sum',
260 |     hue='Sales Channel',
261 |     palette='Set2',
262 |     legend=False,
263 |     errorbar=None
264 | )
265 | plt.title("Total Sales by Channel")
266 | plt.ylabel("Total Sales ($)")
267 | plt.tight_layout()
268 | plt.show()
269 | 
270 | 
271 | # Pie Chart: Contribution of Each Channel
272 | plt.figure(figsize=(6, 6))
273 | plt.pie(
274 |     channel_summary['sum'],
275 |     labels=channel_summary['Sales Channel'],
276 |     autopct='%1.1f%%',
277 |     colors=sns.color_palette('Set2')
278 | )
279 | plt.title("Sales Contribution: Retail vs Warehouse")
280 | plt.tight_layout()
281 | plt.show()
282 | 
283 | # Objective 3: Top Performing Products
284 | 
285 | # Create Total Sales column (if not already added)
286 | df['Total Sales'] = df['RETAIL SALES'] + df['WAREHOUSE SALES']
287 | 
288 | # 1️⃣ Top Products by Total Sales
289 | top_products_total = df.groupby('ITEM TYPE')['Total Sales'].sum().sort_values(ascending=False).head(10).reset_index()
290 | 
291 | # 2️⃣ Top Products by Retail Sales
292 | top_products_retail = df.groupby('ITEM TYPE')['RETAIL SALES'].sum().sort_values(ascending=False).head(10).reset_index()
293 | 
294 | # 3️⃣ Top Products by Warehouse Sales
295 | top_products_warehouse = df.groupby('ITEM TYPE')['WAREHOUSE SALES'].sum().sort_values(ascending=False).head(10).reset_index()
296 | 
297 | # 🔹 Horizontal Bar Plot for Top Products by Total Sales
298 | plt.figure(figsize=(10, 6))
299 | sns.barplot(
300 |     data=top_products_total,
301 |     y='ITEM TYPE',
302 |     x='Total Sales',
303 |     hue='ITEM TYPE',
304 |     palette='Blues_d',
305 |     legend=False,
306 |     errorbar=None  # remove confidence intervals
307 | )
308 | plt.title("Top 10 Products by Total Sales")
309 | plt.xlabel("Total Sales ($)")
310 | plt.ylabel("Product")
311 | plt.tight_layout()
312 | plt.show()
313 | 
314 | # 🔹 Horizontal Bar Plot for Top Products by Retail Sales
315 | plt.figure(figsize=(10, 6))
316 | sns.barplot(
317 |     data=top_products_retail,
318 |     y='ITEM TYPE',
319 |     x='RETAIL SALES',
320 |     hue='ITEM TYPE',
321 |     palette='Greens_d',
322 |     legend=False,
323 |     errorbar=None
324 | )
325 | plt.title("Top 10 Products by Retail Sales")
326 | plt.xlabel("Retail Sales ($)")
327 | plt.ylabel("Product")
328 | plt.tight_layout()
329 | plt.show()
330 | 
331 | # 🔹 Horizontal Bar Plot for Top Products by Warehouse Sales
332 | plt.figure(figsize=(10, 6))
333 | sns.barplot(
334 |     data=top_products_warehouse,
335 |     y='ITEM TYPE',
336 |     x='WAREHOUSE SALES',
337 |     hue='ITEM TYPE',
338 |     palette='Oranges_d',
339 |     legend=False,
340 |     errorbar=None
341 | )
342 | plt.title("Top 10 Products by Warehouse Sales")
343 | plt.xlabel("Warehouse Sales ($)")
344 | plt.ylabel("Product")
345 | plt.tight_layout()
346 | plt.show()
347 | 
348 | # Objective 4:  Correlation Between Product Price and Sales Volume
349 | 
350 | # Filter out rows with 0 transfers to avoid divide-by-zero
351 | df_valid = df[df['RETAIL TRANSFERS'] > 0].copy()
352 | 
353 | # Calculate approximate price per unit
354 | df_valid['PRICE PER UNIT'] = df_valid['RETAIL SALES'] / df_valid['RETAIL TRANSFERS']
355 | 
356 | # Display correlation
357 | correlation = df_valid[['PRICE PER UNIT', 'RETAIL TRANSFERS']].corr()
358 | print("🔗 Correlation Matrix:")
359 | print(correlation)
360 | 
361 | # Scatter plot with regression line
362 | plt.figure(figsize=(8, 6))
363 | sns.regplot(data=df_valid, x='PRICE PER UNIT', y='RETAIL TRANSFERS', scatter_kws={'alpha':0.5})
364 | plt.title("Correlation Between Product Price and Quantity Sold")
365 | plt.xlabel("Price Per Unit ($)")
366 | plt.ylabel("Quantity Sold (Retail Transfers)")
367 | plt.tight_layout()
368 | plt.show()
369 | 
370 | # Objective 5:  Peak Sales Months
371 | 
372 | # Create datetime column
373 | df['DATE'] = pd.to_datetime(df['YEAR'].astype(str) + '-' + df['MONTH'].astype(str) + '-01')
374 | 
375 | # Extract month name for visualization
376 | df['MONTH_NAME'] = df['DATE'].dt.strftime('%B')
377 | 
378 | # Calculate total sales
379 | df['TOTAL SALES'] = df['RETAIL SALES'] + df['WAREHOUSE SALES']
380 | 
381 | # Order the months
382 | month_order = ['January', 'February', 'March', 'April', 'May', 'June',
383 |                'July', 'August', 'September', 'October', 'November', 'December']
384 | 
385 | # Group and sort data
386 | monthly_sales = df.groupby('MONTH_NAME')['TOTAL SALES'].sum().reindex(month_order)
387 | 
388 | # Plot the result without emoji and FutureWarning
389 | plt.figure(figsize=(10, 6))
390 | sns.barplot(x=monthly_sales.index, y=monthly_sales.values)
391 | plt.xticks(rotation=45)
392 | plt.title("Total Sales by Month")  
393 | plt.xlabel("Month")
394 | plt.ylabel("Total Sales")
395 | plt.tight_layout()
396 | plt.show()
397 | 


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