├── Project.py
├── README.md
└── railway.csv


/Project.py:
--------------------------------------------------------------------------------
  1 | import pandas as pd
  2 | import numpy as np
  3 | import seaborn as sns
  4 | import matplotlib.pyplot as plt
  5 | data= pd.read_csv("D:/UK+Train+Rides/railway.csv")
  6 | #Display Basic info
  7 | print(data.info())
  8 | print(data.head())
  9 | 
 10 | #check for missing values
 11 | missing_values = data.isnull().sum()
 12 | print(missing_values)
 13 | 
 14 | #Handling the missing values
 15 | 
 16 | 
 17 | 
 18 | #Drop rows with critical missing values
 19 | data.dropna(subset=['Price', 'Departure Station', 'Arrival Destination'], inplace=True)
 20 | 
 21 | # Fill missing delay reasons with 'No Delay'
 22 | data['Reason for Delay'].fillna('No Delay', inplace=True)
 23 | 
 24 | # Fill missing 'Refund Request' with 'No'
 25 | data['Refund Request'].fillna('No', inplace=True)
 26 | 
 27 | # Fill missing 'Railcard' with 'No Railcard'
 28 | data['Railcard'].fillna('No Railcard', inplace=True)
 29 | 
 30 | # Fill missing 'Actual Arrival Time' with 'mode of Actual Arrival Time'
 31 | data['Actual Arrival Time'].fillna(data["Actual Arrival Time"].mode()[0], inplace=True)
 32 | 
 33 | #1. Objective Ticket Sales Trends by Line Plot Graph
 34 | 
 35 | data['Date of Purchase'] = pd.to_datetime(data['Date of Purchase'])
 36 | 
 37 | sales_over_time = data.groupby('Date of Purchase')['Price'].sum()
 38 | plt.figure(figsize=(10, 6))
 39 | sales_over_time.plot(kind='line')
 40 | plt.title('Total Sales Over Time')
 41 | plt.xlabel('Date')
 42 | plt.ylabel('Total Sales (£)')
 43 | plt.grid(True)
 44 | plt.show()
 45 | 
 46 | #2. Objective Delay Patterns  on Heatmap
 47 | 
 48 | data['Departure Hour'] = pd.to_datetime(data['Departure Time'], format='%H:%M:%S').dt.hour
 49 | 
 50 | delayed_data = data[data['Journey Status'] == 'Delayed']
 51 | 
 52 | heatmap_data = delayed_data.pivot_table(index='Departure Station', columns='Departure Hour', aggfunc='size', fill_value=0)
 53 | 
 54 | plt.figure(figsize=(14, 8))
 55 | sns.heatmap(heatmap_data, cmap='Reds', annot=True, fmt='d')
 56 | plt.title('Number of Delays by Station and Hour')
 57 | plt.xlabel('Hour of Day')
 58 | plt.ylabel('Departure Station')
 59 | plt.show()
 60 | 
 61 | #3. Objective Ticket Pricing Insights on Box plot
 62 | 
 63 | plt.figure(figsize=(10, 6))
 64 | sns.boxplot(data=data, x='Ticket Type', y='Price',palette='magma')
 65 | plt.title('Ticket Prices by Ticket Type')
 66 | plt.xlabel('Ticket Type')
 67 | plt.ylabel('Price (£)')
 68 | plt.grid(True)
 69 | plt.show()
 70 | 
 71 | #4. Objective Journey Delays on Bar Chart
 72 | 
 73 | data['Scheduled Arrival'] = pd.to_datetime(data['Arrival Time'], format='%H:%M:%S')
 74 | 
 75 | data['Actual Arrival'] = pd.to_datetime(data['Actual Arrival Time'], format='%H:%M:%S')
 76 | 
 77 | data['Delay Minutes'] = (data['Actual Arrival'] - data['Scheduled Arrival']).dt.total_seconds() / 60
 78 | 
 79 | data['Route'] = data['Departure Station'] + ' → ' + data['Arrival Destination']
 80 | 
 81 | route_delays = data.groupby('Route')['Delay Minutes'].mean().dropna()
 82 | 
 83 | plt.figure(figsize=(14, 8))
 84 | route_delays.sort_values(ascending=False).plot(kind='bar')
 85 | plt.title('Average Delay by Route')
 86 | plt.xlabel('Route')
 87 | plt.ylabel('Average Delay (minutes)')
 88 | plt.grid(True)
 89 | plt.show()
 90 | 
 91 | #5. Objective Price vs Journey Distance on Scatter Plot
 92 | 
 93 | np.random.seed(0)
 94 | data['Estimated Distance (km)'] = np.random.randint(50, 500, size=len(data))
 95 | 
 96 | plt.figure(figsize=(10, 6))
 97 | plt.scatter(data['Estimated Distance (km)'], data['Price'],color='crimson')
 98 | plt.title('Ticket Price vs Estimated Journey Distance')
 99 | plt.xlabel('Estimated Distance (km)')
100 | plt.ylabel('Price (£)')
101 | plt.grid(True)
102 | plt.show() 
103 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # EDA-For-Python
2 | This project performs Exploratory Data Analysis on UK railway ticket data. It includes visual insights into ticket sales trends, delay patterns by station and time, ticket pricing distributions, route-based journey delays, and the relationship between price and estimated travel distance. 
3 | 


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