Safety precaution for driving in Indian roads

-



Presenting by Madhan Kumar Selvaraj


 India has 1% of the world's vehicles but accounts for 6% of the world's road traffic accidents. What is the root cause for it and what are the measures we can take to minimize these accidents?

What this project is about 

Analyzing the road accident data from the Indian government website and suggesting a few important safety measures for the travelers.

Basic flow chart of the project

In this blog, we are going to know the root cause of the accident by using the following technology
  • Python
  • Pandas
  • Seaborn
  • MySQL
  • Flask
  • Jinja web template

Prerequisite

  • Python 3.X version
    • Refer my blog where you will get all the reference link to install Python and other dependencies
  • Anaconda for Jupyter notebook
    • From this site, you will get Conda, Jupyter notebook, Spyder IDE and many more
  • Pycharm IDE (Optional)
    • I personally like this IDE for Python coding. Refer my previous blog
  • MySQL server
    • Download MySQL from the official site and select the option of MySQL server while installing 

 The workflow of this project 

  1. Downloading the needed accident reports from the government website
  2. Analyzing the downloaded dataset by EDA (Exploratory Data Analysis)
  3. Load the result data into the MySQL database
  4. Creating a webpage to get data from the user
  5. Suggesting the safety precaution ideas to the user

 Road accident dataset

Download the dataset from the Indian government website and I used only the below accidents category dataset. You can get those selected datasets from here.
  1. The accident report from the year 1970 to 2017
  2. Accidents due to weather condition
  3. Reports based on the time
  4. Persons killed without using helmets
  5. The accident reports based on the place
  6. Accidents happened due to vehicle defects
  7. State-wise reports in the year 2017
  8. Person killed per thousand population

Exploratory Data Analysis

I upload the exploratory data analyzing Jupyter's notebook file in the kaggle.  Refer the EDA file to get to know the techniques of analyzing any kind of dataset. Here I added a few statistics reports from the EDA process.
 Accidents report from the year 1970 to 2017
 Total and fatal accidents across the states
 Accidents happened due to driver's irresponsibility
 Person killed without using the helmet
 Accidents based on per thousand population across the states
In the EDA process, we analyzed the data based on certain rules and also set threshold values for each criterion. Now we need to load the data into the database.

Loading data into the database

I am using the MySQL database to load the data. Create the database name "indian_road_accident" by using the below command
Move the file that we create in the EDA process to this location "C:\ProgramData\MySQL\MySQL Server 8.0\Uploads". Also, edit the "my.ini" file by following the below image to load data from CSV file into the database
Create the table schema by running the below code

 
CREATE TABLE Accident(States_UTs VARCHAR(255), Fatal_Accidents VARCHAR(255), Without_using_helmet VARCHAR(255),Intake_of_Alcohal VARCHAR(255), Exceeding_lawful_speed VARCHAR(255), Jumping_Red_Light VARCHAR(255),Driving_on_wrong_side VARCHAR(255), Jumping_Changing_lanes VARCHAR(255), Overtaking VARCHAR(255),Using_Mobile_Phones_while_driving VARCHAR(255), Asleep_or_Fatigued_or_Sick VARCHAR(255),Near_School_College_any_other_educational_Institutes VARCHAR(255),Pedestrian_crossing VARCHAR(255), Market_Place VARCHAR(255), Near_a_Religious_Place VARCHAR(255),Near_Hospital VARCHAR(255), Narrow_bridge_or_culverts VARCHAR(255), Near_Petrol_Pump VARCHAR(255),Near_Bus_Stand VARCHAR(255), Near_or_on_Road_under_Construction VARCHAR(255), 06_900hrs VARCHAR(255),09_1200hrs VARCHAR(255), 12_1500hrs VARCHAR(255), 15_1800hrs VARCHAR(255), 18_2100hrs VARCHAR(255), 21_2400hrs VARCHAR(255),00_300hrs VARCHAR(255), 03_600hrs VARCHAR(255), Defective_brakes VARCHAR(255), Defective_Steering_Axil VARCHAR(255),Punctured_burst_Typres VARCHAR(255), Worn_out_Tyres VARCHAR(255), Mist_fog VARCHAR(255), Cloudy VARCHAR(255),Heavy_rain VARCHAR(255), Flooding_of_slipways_rivulers VARCHAR(255), Hail_sleet VARCHAR(255), snow VARCHAR(255),Strong_wind VARCHAR(255), Dust_storm VARCHAR(255), Very_hot VARCHAR(255), Very_cold VARCHAR(255));
Loading CSV file into the database
 
LOAD DATA INFILE "C:\\ProgramData\\MySQL\\MySQL Server 8.0\\Uploads\\Road_accident_dataset.csv" INTO TABLE accident  FIELDS TERMINATED BY ','  ENCLOSED BY '"' LINES TERMINATED BY '\n' IGNORE 1 ROWS;
Run the below command to check the DB

Creating a webpage to get user data

I used Python flask and Jinja web template to create a web page. Below I listed the work of each file
  • flask_file.py
    • It takes care of all the web page related work like using CSS, Javascript, JQuery
    • Creating a dynamic table using the Jinja web template
  • main.py
    •  The main controller that connects with flask and MySQL
  • accident_database.py
    • Fetching data from the database
  •  HTML files
    • upload.html
      • Used to get the data from the user
    • statistics.html
      • Used to publish the result to the user 
Flask_file.py 
import os
from main import execution
from flask import Flask, render_template, request

image_folder = os.path.join('static', 'image')
app = Flask(__name__)
app.config['UPLOAD_FOLDER'] = image_folder
app.debug = True

# route and function to handle the form page
@app.route('/', methods=['GET', 'POST'])
def upload_page():
    if request.method == 'POST':
        user_selected_values = request.form.getlist("accident") # Getting values given by user
        suggestion, accident_threshold_value, overall_safety = execution(user_selected_values)
        negative_value_count = sum(n < 0 for n in accident_threshold_value) # Checking total numer of negative difference values
        year_chart = os.path.join(app.config['UPLOAD_FOLDER'], 'year.png')
        fatal_accident = os.path.join(app.config['UPLOAD_FOLDER'], 'fatal_accident.png')
        irresponsibility = os.path.join(app.config['UPLOAD_FOLDER'], 'irresponsibility.png')
        print(overall_safety)
        return render_template('statistics.html', suggestion= suggestion, accident_threshold_value=accident_threshold_value , overall_safety=overall_safety, negative_value_count = negative_value_count, year_chart=year_chart, fatal_accident=fatal_accident, irresponsibility=irresponsibility)
    elif request.method == 'GET':
        return render_template('upload.html')

if __name__ == '__main__':
    app.run(debug=True)
Main.py
 
import pandas as pd
import configuration  # importing values from configuration file
from accident_database import mysql_data
feature = []
suggestion = []
def execution(feature_keys):
    for data in feature_keys:
        data = int(data)
        if data in configuration.feature_dict.keys():
            feature.append(configuration.feature_dict[data]) # Separating feature name to use in SQL query based on key
        elif data in configuration.state_dict.keys():
            state_name = configuration.state_dict[data] # Separating state name to use in SQL query based on key
    fetch_data = mysql_data(state_name, feature) # calling MYSQL to execute the query
    actual_value = pd.Series(fetch_data[0]) # Contains values for each feature
    threshold_value = pd.Series(fetch_data[1]) # Contains threshold values for each feature
    difference_value = threshold_value.astype('float') - actual_value.astype('float')  # Variance from the threshold
    # Formula based on the weightage
    # 50% value for difference value lesser than -5
    # 25% value for difference value between -3 and -5
    # 10% value for difference value between 0 and -3
    # 8% value for difference value between 0 and 3
    # 5% value for difference value between 3 and 5
    # 2% value for difference value greater than 5
    accident_threshold_value = difference_value.apply(
        lambda x: x * 5 / 100 if (3.0 < x < 5.0) else (x * 8 / 100 if (0 < x < 3.0) else (
            x * 10 / 100 if (-3 < x < 0) else (
                x * 25 / 100 if (-5 < x < -3) else (x * 50 / 100 if (x < -5) else x * 2 / 100)))))
    for data in feature:
        if data in configuration.user_suggestion.keys():
            suggestion.append(configuration.user_suggestion[data]) # Appending suggestion data to publish in webpage
    overall_safety = accident_threshold_value.sum() # Overall safety status of the travel
    # accident_threshold_dict = dict(zip(suggestion, accident_threshold_value))
    return suggestion, accident_threshold_value, overall_safety
These two are the important files and the remaining files you can download from the end of this blog. Now we'll move to the output part.
 Run the "flask_file.py" file and you will the result like below
Open the http://127.0.0.1:5000/ link in the browser
Used Bootstrap CSS to have rich look in the webpage and you can check other features in the CSS files
After submitting your travel details, you will get safety precaution suggestion and alerting the risk status based on the values you are feeding.
 Safe to travel status
Warning alert for travel
Danger alert to take precaution immediately

Code in Github

Get this project complete code from here

Finally, Tamilnadu and Uttar Pradesh are having a high accident rate and we can control by driving in lawful speed and driving carefully during worse climate respectively.
P.s: Mental illness affects one in four people as per the WHO report. Don't compare yourself with anyone and everyone's track is different. Valuable comments and suggestions are always welcome.

Comments

Post a Comment

Popular posts from this blog

Artificial Intelligent Chatbot

-
Image
Presenting by Madhan Kumar Selvaraj Globally 30% of the customer service is handling by the Chatbot. Its market size is projected to grow from $2.6 billion in 2019 to $9.4 billion by 2024. Many of the people have a thought that machines will grab their job. But the reality is that the machine assist humans to do the complicated woks in a easy manner. What this blog is about? This blog helps you to create an Artificial intelligent Chatbot by deploying it in the Python Flask web framework and the Heroku cloud platform. Here I am doing this chatbot to assist a coaching institute to respond to the students regarding the course details and also it can answer questions apart from the course. Everyone knows about Google assistant, Apple's Siri, Microsoft's Cortona, Amazon's Alexa. Our Chatbot also works like the same and it is having limitation because we are using limited pattern and response. If we add more pattern and response, it can response to all our queries. Chatbot A c...
Read more

Detecting stranger through CCTV camera and alerting the owner

-
Image
Presenting by Madhan Kumar Selvaraj In this blog, we are going to see some interesting stuff related to detection. Globally there are around 25 million CCTV cameras in the house. Sadly, for every 3 minutes robbery, theft and burglary are happening. Real-world issue Even though we have access to live streaming CCTV video footage through the internet. But most of the time we failed to check the video footage at the time of the robbery. So, there is a need for a smart alert system. One-liner of the project Detecting the human subject other than the family members through the CCTV footage and alerting the house owner through the mail. Technologies used here OpenCV computer vision Facenet CNN model MTCNN (Multi-task Cascaded Convolutional Neural Networks) Support Vector Machine algorithm Matplotlib library The workflow of the project Focusing only on the human subject in the CCTV footage other than animals, birds, etc Take a screenshot of the video once we ...
Read more

Extracting text from the image and translation using Tesseract and Yandex API

-
Image
Presenting by Madhan Kumar Selvaraj Text extraction from the image and translation  In this blog, we will learn about the process of extracting the text from the image by using the open-source Google's Optical Character Recognition OCR engine  Tesseract. Then we will use the multiple language detector and translator Yandex API to detect and translate the language of the text and the image. What is OCR ? OCR refers to Optical Character Recognition. As a human we can able to recognize the text from the image but what about the computer and how it can read or parse the data from the image. At that time we found the OCR and inside the OCR engine, there will be computer vision for the image processing and machine learning technique to train the machine with training data set using certain algorithms to improve the accuracy. What are the benefits of learning and using OCR? The ultimate benefit of the OCR is to convert the hard copy into the digital format. Still ...
Read more