EFFICIENT APPROACH TO PREDICT EXACT DATA USING MACHINE LEARNING BASED ON YIELDING DATASET









Abstract

Agriculture is the science and practice of growing plants and animals. Agriculture is India's second largest industry, accounting for 60.45% of the country's land area. Agriculture and agro-industry products account for the majority of the Indian economy. Crop rotation, soil clamminess, air and surface temperature, precipitation, and other factors all have a part in the cultivation process. This project seeks to gather and analyze data on temperature, rainfall, soil, seed, crop productivity, humidity, and wind speed (in a few places) in order to assist farmers in improving agricultural yield. Preprocess the data in a Python environment first, then use the MapReduce framework to examine and process the massive amount of data. Second, k-means clustering is applied to MapReduce results, yielding a mean result on the data in terms of accuracy. Then, using bar graphs and scatter plots, investigate the link between two locations' crops, rainfall, temperature, soil, and seed type. Furthermore, a self-designed recommender system was utilized to forecast the crops and present them on a Flask-based Graphic User Interface. Some fundamental information is necessary to increase crop quality, such as plant selection and soil parameters like pH, which play a vital influence in obtaining a decent yield. It's also crucial to choose the correct seeds and calculate how much fertilizer and insecticide you'll need.


Modules


Algorithms


Software And Hardware