├── Dealer Wise Particular Part Stock (2).csv
└── ca2 project.py


/ca2 project.py:
--------------------------------------------------------------------------------
  1 | import numpy as np
  2 | import pandas as pd
  3 | import matplotlib.pyplot as plt
  4 | import seaborn as sn
  5 | 
  6 | df=pd.read_csv("C:/Users/anusr/OneDrive/Desktop/CA 2 Project 12319748/Dealer Wise Particular Part Stock (2).csv")
  7 | print(df)
  8 | print(df.head())
  9 | 
 10 | print(df.info())
 11 | 
 12 | print(df.describe())
 13 | 
 14 | t = df.isnull().sum()
 15 | print("Null Values count:",t)
 16 | 
 17 | print("Total null values:", df.isnull().sum().sum())
 18 | print(df['Zonal Office'].isnull().sum())
 19 | print(df['Area Office'].isnull().sum())
 20 | print(df['Dealer Name'].isnull().sum())
 21 | print(df['Inventory Location'].isnull().sum())
 22 | print(df['Part Number'].isnull().sum())
 23 | print(df['Part Description'].isnull().sum())
 24 | print(df['Stock QTY'].isnull().sum())
 25 | print(df['RATE'].isnull().sum())
 26 | print(df['Amount'].isnull().sum())
 27 | print(df.columns.tolist())
 28 | 
 29 | 
 30 | if 'Stock QTY' in df.columns:
 31 |     print(df['Stock QTY'] == df['Stock QTY'].fillna(0))  
 32 |     print(df['Stock QTY'])                               
 33 | else:
 34 |     print(" 'Stock QTY' column not found!")
 35 | 
 36 | print("\nMissing values per column:\n", df.isnull().sum())
 37 | print("\nAny missing values at all?:", df.isnull().values.any())
 38 | df['Zonal Office']=df['Zonal Office'].fillna('Unknown')
 39 | print(df['Zonal Office'])
 40 | print(df.isnull().sum())        
 41 | print(df.isnull().values.any())
 42 | df['Area Office']=df['Area Office'].fillna('Unknown')
 43 | print(df['Area Office'])
 44 | print(df.isnull().sum())        
 45 | print(df.isnull().values.any())
 46 | df['Dealer Name']=df['Dealer Name'].fillna('Unknown')
 47 | print(df['Dealer Name'])
 48 | print(df.isnull().sum())       
 49 | print(df.isnull().values.any())
 50 | df['Inventory Location']=df['Inventory Location'].fillna('Unknown')
 51 | print(df['Inventory Location'])
 52 | print(df.isnull().sum())      
 53 | print(df.isnull().values.any())
 54 | df['Part Number']=df['Part Number'].fillna(0)
 55 | print(df['Part Number'])
 56 | print(df.isnull().sum())        
 57 | print(df.isnull().values.any())
 58 | df['Part Description']=df['Part Description'].fillna('Unknown')
 59 | print(df['Part Description'])
 60 | print(df.isnull().sum())        
 61 | print(df.isnull().values.any())
 62 | df['RATE']=df['RATE'].fillna(0)
 63 | print(df['RATE'])
 64 | print(df.isnull().sum())       
 65 | print(df.isnull().values.any())
 66 | df['Amount']=df['Amount'].fillna(0)
 67 | print(df['Amount'])
 68 | print(df.isnull().values.any())
 69 | print(df.isnull().sum())        
 70 | print(df.isnull().values.any())
 71 | #Objective 1:Visualize the top 10 parts by their inventory value (sum of "Amount") in a horizontal bar chart.
 72 | top_parts = df.groupby("Part Number", as_index=False)["Amount"].sum()
 73 | top_parts = top_parts.nlargest(10, "Amount").sort_values("Amount")
 74 | plt.figure(figsize=(7, 4))
 75 | sn.barplot(data=top_parts, x="Part Number", y="Amount", color='darkgreen')
 76 | plt.title("Top 10 Part Numbers by Inventory Value")
 77 | plt.xlabel("Part Number")
 78 | plt.ylabel("Inventory Value (INR)")
 79 | plt.xticks(rotation=45)
 80 | plt.tight_layout()
 81 | plt.show()
 82 | #Objective 2:To identify which zones (represented by the top 10 dealers) hold more expensive inventory by analyzing the inventory value using a box plot.
 83 | top_dealers = df.groupby('Dealer Name')['Amount'].sum().nlargest(10).index
 84 | df_top = df[df['Dealer Name'].isin(top_dealers)]
 85 | plt.figure(figsize=(7, 5))
 86 | sn.boxplot(data=df_top, x='Dealer Name', y='Amount', palette='husl',legend=False,hue='Dealer Name')
 87 | plt.title('Distribution of Inventory Value (Amount) for Top 10 Dealers')
 88 | plt.xlabel('Dealer Name')
 89 | plt.ylabel('Inventory Value (Amount)')
 90 | plt.xticks(rotation=45)
 91 | plt.tight_layout()
 92 | plt.show()
 93 | #Objective 3:To visualize and analyze the unit rates of the top 20 most frequently occurring part descriptions in the dataset using a line plot.
 94 | plt.figure(figsize=(7, 5))
 95 | top_parts = df["Part Description"].value_counts().head(20).index
 96 | filtered_df = df[df["Part Description"].isin(top_parts)]
 97 | sn.lineplot(data=filtered_df, x="Part Description", y="RATE", marker="*", linewidth=2)
 98 | plt.xticks(rotation=90)
 99 | plt.title("Rate by Part Description")
100 | plt.xlabel("Part Description")
101 | plt.ylabel("Rate (Unit Price)")
102 | plt.tight_layout()
103 | plt.grid(True)
104 | plt.show()
105 | #Objective 4:To analyze the relationship between Stock Quantity and Rate of parts across dealers by visualizing their correlation using a heatmap
106 | corr_matrix = df[["Stock QTY", "RATE", ]].corr()
107 | plt.figure(figsize=(6, 5))
108 | sn.heatmap(corr_matrix, annot=True, cmap="coolwarm", fmt=".2f")
109 | plt.title("Correlation Heatmap: Stock QTY, RATE")
110 | plt.show()
111 | #Objective 5:To visualize the distribution and frequency of stock quantities across all parts using a histogram.
112 | 
113 | plt.figure(figsize=(6, 5))
114 | plt.hist(data=df, x="Stock QTY", bins=30,  color="black")
115 | plt.title("Histogram of Stock Quantity")
116 | plt.show()
117 | 
118 | 


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