ML Part of Product Based Bangkit Capstone Project Team C22-PS316

We are making a crop recommendation system for recommending the top 5 crops to be grown based on the users city and environment.

• Python
• TensorFlow
• Flask
• OpenWeatherMap API
• Google Cloud Run
• Google Colab

Click here ( Deployed using Google Cloud Run )

In our machine learning model we use a deep neural network with 4 layers, 1 layer for input with input_dim is 5 which will enter 5 data, namely temperature, humidity, rainfall, soil, and light, then 2 layers for the hidden layer, and the last 1 layer for the output, in the output layer we use softmax activation so that later we can take a sequence of 5 predictions with the highest accuracy. Here we can see after we train the model we get 33% loss and 89% accuracy, from this training result as you can see highest accuracy prediction and actual data are the same and then it will be followed up to second-highest accuracy to the fifth-highest accuracy

• Clone this repo
• Open terminal and go to this project's root directory
• Create your own OpenWeatherMap API_KEY (*Notes)
• Create a config.py file and type api_key="your_api_key" then save
• Create and activate a python virtual environment if you want
• Type pip install -r requirements.txt
• Serve the Flask app by typing flask run
• It will run on http://127.0.0.1:5000