Understanding gender differences in professional European football through Machine Learning interpretability and match actions data. This repository contains the full data pipeline implemented for the study *Understanding gender differences in professional European football through Machine Learning interpretability and match actions data*. We evaluated European male, and female football players' main differential features in-match actions data under the assumption of finding significant differences and established patterns between genders. A methodology for unbiased feature extraction and objective analysis is presented based on data integration and machine learning explainability algorithms. Female (1511) and male (2700) data points were collected from event data categorized by game period and player position. Each data point included the main tactical variables supported by research and industry to evaluate and classify football styles and performance. We set up a supervised classification pipeline to predict the gender of each player by looking at their actions in the game. The comparison methodology did not include any qualitative enrichment or subjective analysis to prevent biased data enhancement or gender-related processing. The pipeline had three representative binary classification models; A logic-based Decision Trees, a probabilistic Logistic Regression and a multilevel perceptron Neural Network. Each model tried to draw the differences between male and female data points, and we extracted the results using machine learning explainability methods to understand the underlying mechanics of the models implemented. A good model predicting accuracy was consistent across the different models deployed. ## Installation Install the required python packages ``` pip install -r requirements.txt ``` To handle heterogeneity and performance efficiently, we use PySpark from [Apache Spark](https://spark.apache.org/). PySpark enables an end-user API for Spark jobs. You might want to check how to set up a local or remote Spark cluster in [their documentation](https://spark.apache.org/docs/latest/api/python/index.html). ## Repository structure This repository is organized as follows: - Preprocessed data from the two different data streams is collecting in [the data folder](data/). For the Opta files, it contains the event-based metrics computed from each match of the 2017 Women's Championship and a single file calculating the event-based metrics from the 2016 Men's Championship published [here](https://figshare.com/collections/Soccer_match_event_dataset/4415000/5). Even though we cannot publish the original data source, the two python scripts implemented to homogenize and integrate both data streams into event-based metrics are included in [the data gathering folder](data_gathering/) folder contains the graphical images and media used for the report. - The [data cleaning folder](data_cleaning/) contains descriptor scripts for both data streams and [the final integration](data_cleaning/merger.py) - [Classification](classification/) contains all the Jupyter notebooks for each model present in the experiment as well as some persistent models for testing.

This repository demonstrates how to use Jupyter Notebooks to create dynamic, interactive reports that are updated and exported automatically. By combining Python scripts with a pipeline, we ensure that both the data and the reports remain up to date without manual intervention.

Potato Disease Classification Setup for Python: Install Python (Setup instructions) Install Python packages pip3 install -r training/requirements.txt pip3 install -r api/requirements.txt Install Tensorflow Serving (Setup instructions) Setup for ReactJS Install Nodejs (Setup instructions) Install NPM (Setup instructions) Install dependencies cd frontend npm install --from-lock-json npm audit fix Copy .env.example as .env. Change API url in .env. Setup for React-Native app Initial setup for React-Native app(Setup instructions) Install dependencies cd mobile-app yarn install cd ios && pod install && cd ../ Copy .env.example as .env. Change API url in .env. Training the Model Download the data from kaggle. Only keep folders related to Potatoes. Run Jupyter Notebook in Browser. jupyter notebook Open training/potato-disease-training.ipynb in Jupyter Notebook. In cell #2, update the path to dataset. Run all the Cells one by one. Copy the model generated and save it with the version number in the models folder. Running the API Using FastAPI Get inside api folder cd api Run the FastAPI Server using uvicorn uvicorn main:app --reload --host 0.0.0.0 Your API is now running at 0.0.0.0:8000 Using FastAPI & TF Serve Get inside api folder cd api Copy the models.config.example as models.config and update the paths in file. Run the TF Serve (Update config file path below) docker run -t --rm -p 8501:8501 -v C:/Code/potato-disease-classification:/potato-disease-classification tensorflow/serving --rest_api_port=8501 --model_config_file=/potato-disease-classification/models.config Run the FastAPI Server using uvicorn For this you can directly run it from your main.py or main-tf-serving.py using pycharm run option (as shown in the video tutorial) OR you can run it from command prompt as shown below, uvicorn main-tf-serving:app --reload --host 0.0.0.0 Your API is now running at 0.0.0.0:8000 Running the Frontend Get inside api folder cd frontend Copy the .env.example as .env and update REACT_APP_API_URL to API URL if needed. Run the frontend npm run start Running the app Get inside mobile-app folder cd mobile-app Copy the .env.example as .env and update URL to API URL if needed. Run the app (android/iOS) npm run android or npm run ios Creating the TF Lite Model Run Jupyter Notebook in Browser. jupyter notebook Open training/tf-lite-converter.ipynb in Jupyter Notebook. In cell #2, update the path to dataset. Run all the Cells one by one. Model would be saved in tf-lite-models folder. Deploying the TF Lite on GCP Create a GCP account. Create a Project on GCP (Keep note of the project id). Create a GCP bucket. Upload the tf-lite model generate in the bucket in the path models/potato-model.tflite. Install Google Cloud SDK (Setup instructions). Authenticate with Google Cloud SDK. gcloud auth login Run the deployment script. cd gcp gcloud functions deploy predict_lite --runtime python38 --trigger-http --memory 512 --project project_id Your model is now deployed. Use Postman to test the GCF using the Trigger URL. Inspiration: https://cloud.google.com/blog/products/ai-machine-learning/how-to-serve-deep-learning-models-using-tensorflow-2-0-with-cloud-functions Deploying the TF Model (.h5) on GCP Create a GCP account. Create a Project on GCP (Keep note of the project id). Create a GCP bucket. Upload the tf .h5 model generate in the bucket in the path models/potato-model.h5. Install Google Cloud SDK (Setup instructions). Authenticate with Google Cloud SDK. gcloud auth login Run the deployment script. cd gcp gcloud functions deploy predict --runtime python38 --trigger-http --memory 512 --project project_id Your model is now deployed. Use Postman to test the GCF using the Trigger URL. Inspiration: https://cloud.google.com/blog/products/ai-machine-learning/how-to-serve-deep-learning-models-using-tensorflow-2-0-with-cloud-functions