The purpose of this research is to gather and analyze a wide range of data related to weather and crop production in specific regions of India. The data includes information on temperature, rainfall, sand, grain, crop production, moisture content, and wind velocity, among others. The aim is to use this information to help farmers improve their crop yields and make more informed decisions about planting and harvesting crops. To achieve this goal, the study employs a method known as big data analytics for weather-based crop prediction. This approach utilizes historical weather data, crop yield, and soil moisture information to forecast future crop yields. Machine learning algorithms are applied to analyze large datasets and identify patterns and trends that can be used to make predictions about future crop yields. The research involves several stages. First, the data is processed using Python to remove any unwanted or noisy data. Next, the MapReduce framework is used to analyze and process the large amount of data collected. Then, k-means clustering is applied to the MapReduce outcomes to group similar data points together and obtain an expected average for the data, which helps in assessing its accuracy. The research also involves the development of a customized approach for predicting and displaying harvest forecasts through a user-friendly interface based on Flask. This approach allows users to make informed decisions about farming practices based on information such as temperature, rainfall, moisture content, and wind velocity. Furthermore, the study recommends three crops for farming and is configurable, allowing for the prediction of the best farms for each region. The research is essential for policymakers and farmers in India as it provides valuable insights into the potential impact of climate change on agricultural production. The study also offers a method for using data analytics to improve crop production, which can help increase food security in India and other countries facing similar challenges.