Analysis and Prediction of Coal Mines all over India.

India is the world's second largest producer of coal after China, having cumulative total coal resources of 319.020 billion tonnes(2k18) and is dependent on coal for many of its core sectors.

Coal is the largest source of electricity generation in India and as per reports, fuels approximately 74% of India's electricity.

In addition to power and electricity, sectors like iron and steel, cement and other industries like fertilisers, pulp and paper are also among the largest consumers of coal in India.

Coal has been mined in India for about two centuries.

Developments in the post-independence period have been significant and strides made since nationalization of the coal industry have been even more impressive.

Coal will continue to be India's prime source of energy for power generation, steel-making, powering of locomotives, and production of cement, fertilizer and domestic fuel.

For this Small Project of mine, I have Analyzed the data from the production of coal in the country. And did the prediction using Machine Learning Algorithms !

• Collected the data from different websites and organized to form a meaningful dataset.
• Did Exploratory Data Analysis on the dataset.
• Visualizations were made by using Matplotlib and Seaborn Libraries.
• Finded correlation to form a Heatmap.

And For Prediction , i used :

• One Hot Encoding
• Hyperparameter Tuning ; RandomizedSearchCV
• RandomForestRegressor

Fitted the Model

And predicted it from the train test split that i had done before.

• Plotted the predictipn graph
• Got a Normal Distribution Curve

Also, checked for errors at last

• Mean Absolute Error
• Root mean Squared Error

Conclusion :

From above , i can say that i was able to make the data meaningful and explained with the perspective of a data scientist. Made visualization and Predicted the model to get a Normal Distribution curve. So, All in all, it was a fun experience.