{"id":18906677,"url":"https://github.com/valentinlibouton/weather_prediction","last_synced_at":"2026-03-05T15:30:19.353Z","repository":{"id":222796914,"uuid":"752998600","full_name":"ValentinLibouton/weather_prediction","owner":"ValentinLibouton","description":"Prediction meteo par machine learning et deep learning (in progress)","archived":false,"fork":false,"pushed_at":"2024-02-16T20:54:08.000Z","size":9846,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-12-31T11:41:39.624Z","etag":null,"topics":["kaggle-dataset"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ValentinLibouton.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-02-05T09:16:03.000Z","updated_at":"2024-02-16T07:48:31.000Z","dependencies_parsed_at":"2024-11-08T09:18:49.271Z","dependency_job_id":"4a106855-5d86-40b3-aeeb-744b172ddf3e","html_url":"https://github.com/ValentinLibouton/weather_prediction","commit_stats":null,"previous_names":["valentinlibouton/weather_prediction"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ValentinLibouton%2Fweather_prediction","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ValentinLibouton%2Fweather_prediction/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ValentinLibouton%2Fweather_prediction/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ValentinLibouton%2Fweather_prediction/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ValentinLibouton","download_url":"https://codeload.github.com/ValentinLibouton/weather_prediction/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239890382,"owners_count":19713956,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["kaggle-dataset"],"created_at":"2024-11-08T09:18:21.227Z","updated_at":"2026-03-05T15:30:19.317Z","avatar_url":"https://github.com/ValentinLibouton.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Models\n1. ## `ML_SGDClassifier.joblib`\n- Meilleurs paramètres trouvés :\u003cbr\u003e\n{'classifier__alpha': 0.001, 'classifier__loss': 'log_loss', 'classifier__max_iter': 1000, 'classifier__penalty': 'l2'}\n- Best score: 0.8429646485528453\n- Rapport de classification :\u003cbr\u003e\n\n    |              | precision | recall | f1-score | support |\n    |--------------|-----------|--------|----------|---------|\n    | False        | 0.86      | 0.95   | 0.90     | 18828   |\n    | True         | 0.72      | 0.48   | 0.58     | 5364    |\n    | accuracy     |           |        | 0.84     | 24192   |\n    | macro avg    | 0.79      | 0.71   | 0.74     | 24192   |\n    | weighted avg | 0.83      | 0.84   | 0.83     | 24192   |\n- Précision du modèle sur l'ensemble des données de test : 0.8257275132275133\n\n2. ## `best_model_in_deep_learning.h5` - une epoch\n- Meilleurs paramètres trouvés :\u003cbr\u003e\n{'model__activation': 'relu', 'model__dropout_rate': 0.3, 'model__kernel_regularizer': None, 'model__learning_rate': 0.001}\n- Best score: 0.8442659139633178\n\n    |              | precision | recall | f1-score | support |\n    |--------------|-----------|--------|----------|---------|\n    | False        | 0.87      | 0.95   | 0.90     | 18828   |\n    | True         | 0.72      | 0.48   | 0.58     | 5364    |\n    | accuracy     |           |        | 0.84     | 24192   |\n    | macro avg    | 0.79      | 0.72   | 0.74     | 24192   |\n    | weighted avg | 0.83      | 0.84   | 0.83     | 24192   |\n- Précision sur les données de test : 0.8444940476190477\n\n3. ## `best_model_in_deep_learning.h5` - 100 epochs\n- Meilleurs paramètres trouvés :\u003cbr\u003e\n{'model__activation': 'relu', 'model__dropout_rate': 0.3, 'model__kernel_regularizer': None, 'model__learning_rate': 0.001}\n  - Best score: 0.8448859333992005\n\n    |              | precision | recall | f1-score | support |\n    |--------------|-----------|--------|----------|---------|\n    | False        | 0.86      | 0.96   | 0.90     | 18828   |\n    | True         | 0.74      | 0.45   | 0.56     | 5364    |\n    | accuracy     |           |        | 0.84     | 24192   |\n    | macro avg    | 0.80      | 0.70   | 0.73     | 24192   |\n    | weighted avg | 0.83      | 0.84   | 0.83     | 24192   |\n- Précision sur les données de test : 0.843584656084656\n\n4. ## `ML_SVClassifier.joblib`\n- Meilleurs paramètres trouvés :\u003cbr\u003e\n{'classifier': SVC(), 'classifier__C': 10, 'classifier__kernel': 'rbf'}\n- Best score: 0.8494750705633111\n\n    |              | precision | recall | f1-score | support |\n    |--------------|-----------|--------|----------|---------|\n    | False        | 0.86      | 0.96   | 0.91     | 18828   |\n    | True         | 0.77      | 0.45   | 0.57     | 5364    |\n    | accuracy     |           |        | 0.85     | 24192   |\n    | macro avg    | 0.81      | 0.71   | 0.74     | 24192   |\n    | weighted avg | 0.84      | 0.85   | 0.83     | 24192   |\n- Précision sur les données de test : 0.836102843915344\n\n5. ## `best_model_in_deep_learning_balanced.h5` - 100 epochs + balanced\n- Meilleurs paramètres trouvés :\u003cbr\u003e\n{'model__activation': 'relu', 'model__dropout_rate': 0.3, 'model__kernel_regularizer': None, 'model__learning_rate': 0.01}\n- Best score: 0.7865973353385926\n\n    |              | precision | recall | f1-score | support |\n    |--------------|-----------|--------|----------|--|\n    | False        | 0.77      | 0.83   | 0.80     | 18958 |\n    | True         | 0.81      | 0.75   | 0.78     | 18834 |\n    | accuracy     |           |        | 0.79     | 37792 |\n    | macro avg    | 0.79      | 0.79   | 0.79     | 37792 |\n    | weighted avg | 0.79      | 0.79   | 0.79     | 37792 |\n- Précision sur les données de test : 0.7903259949195597\n\n6. ## `ML_SGDClassifier_balanced.joblib` - balanced\n- Meilleurs paramètres trouvés :\u003cbr\u003e\n{'classifier__alpha': 0.001, 'classifier__loss': 'hinge', 'classifier__max_iter': 1000, 'classifier__penalty': 'l2'}\n- Best score: 0.7781747080124555\n\n    |              | precision | recall | f1-score | support |\n    |--------------|-----------|--------|----------|--|\n    | False        | 0.77      | 0.79   | 0.78     | 18958 |\n    | True         | 0.78      | 0.76   | 0.77     | 18834 |\n    | accuracy     |           |        | 0.78     | 37792 |\n    | macro avg    | 0.78      | 0.78   | 0.78     | 37792 |\n    | weighted avg | 0.78      | 0.78   | 0.78     | 37792 |\n- Précision sur les données de test : 0.7492061812023709\n\n7. ## `best_model_in_deep_learning_change_layers.h5`\n- Meilleurs paramètres trouvés :\u003cbr\u003e\n{'model__activation': 'relu', 'model__batch_size': 16, 'model__dropout_rate': 0.3, 'model__kernel_regularizer': None, 'model__learning_rate': 0.001}\n- Best score: 0.7868949890136718\n\n    |              | precision | recall | f1-score | support |\n    |--------------|-----------|--------|----------|--|\n    | False        | 0.81      | 0.76   | 0.78     | 18958 |\n    | True         | 0.77      | 0.82   | 0.79     | 18834 |\n    | accuracy     |           |        | 0.79     | 37792 |\n    | macro avg    | 0.79      | 0.79   | 0.79     | 37792 |\n    | weighted avg | 0.79      | 0.79   | 0.79     | 37792 |\n- Précision sur les données de test : 0.7881297629127858\n- Temps d'exécution: 22h42 pour 810 fits\n```python\nGridSearchCV(cv=5,\n             estimator=Pipeline(steps=[('scaler', StandardScaler()),\n                                       ('model',\n                                        \u003ckeras.wrappers.scikit_learn.KerasClassifier object at 0x7f0e19762820\u003e)]),\n             param_grid={'model__activation': ['relu', 'sigmoid', 'tanh'],\n                         'model__batch_size': [16, 32, 64],\n                         'model__dropout_rate': [0.3, 0.4, 0.5],\n                         'model__kernel_regularizer': [None,\n                                                       \u003ckeras.regularizers.L2 object at 0x7f0e19762520\u003e],\n                         'model__learning_rate': [0.001, 0.01, 0.1]},\n             verbose=2)\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvalentinlibouton%2Fweather_prediction","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvalentinlibouton%2Fweather_prediction","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvalentinlibouton%2Fweather_prediction/lists"}