Merge pull request #10 from ThiagoPanini/docs-linreg

Updating docs on LinearRegressor class on trainer module
ThiagoPanini · May 11, 2021 · 102d13f · 102d13f
2 parents 4e1fd47 + 67f7e04
commit 102d13f
Show file tree

Hide file tree

Showing 22 changed files with 706 additions and 651 deletions.
diff --git a/examples/linear_regression/linear_regression.py b/examples/linear_regression/linear_regression.py
@@ -46,16 +46,16 @@
 from sklearn.pipeline import Pipeline
 from sklearn.compose import ColumnTransformer
 from sklearn.impute import SimpleImputer
-from mlcomposer.transformers import FiltraColunas, ModificaTipoPrimitivo, \
-    EliminaDuplicatas, DynamicLogTransformation, DynamicScaler, \
-    DummiesEncoding, AgrupamentoCategoricoFinal, LogTransformation
+from mlcomposer.transformers import ColumnSelection, DtypeModifier, \
+    DropDuplicates, DynamicLogTransformation, DynamicScaler, \
+    DummiesEncoding, CategoricalMapper, LogTransformation
 
 # Modelagem dos dados
 from sklearn.model_selection import train_test_split
 from sklearn.linear_model import LinearRegression, Lasso, Ridge, ElasticNet
 from sklearn.tree import DecisionTreeRegressor
 from sklearn.ensemble import RandomForestRegressor
-from mlcomposer.trainer import RegressorLinear
+from mlcomposer.trainer import LinearRegressor
 
 
 """
@@ -112,8 +112,8 @@
 
 # Pipeline inicial de preparação de dados
 initial_prep_pipeline = Pipeline([
-    ('col_filter', FiltraColunas(features=INITIAL_FEATURES)),
-    ('cat_agrup', AgrupamentoCategoricoFinal(cat_dict=CAT_GROUP_DICT, other_tag=OTHER_TAG)),
+    ('col_filter', ColumnSelection(features=INITIAL_FEATURES)),
+    ('cat_agrup', CategoricalMapper(cat_dict=CAT_GROUP_DICT, other_tag=OTHER_TAG)),
     ('log_target', LogTransformation(cols_to_log=TARGET))
 ])
 
@@ -276,7 +276,7 @@
 """
 
 # Instanciando trainer e aplicando treinamento
-trainer = RegressorLinear()
+trainer = LinearRegressor()
 
 # Realizando treinamento e avaliação dos modelos
 trainer.training_flow(set_regressors, X_train_prep, y_train, X_val_prep, y_val, 

diff --git a/examples/linear_regression/output/imgs/feature_importances.png b/examples/linear_regression/output/imgs/feature_importances.png
diff --git a/examples/linear_regression/output/metrics/metrics.csv b/examples/linear_regression/output/metrics/metrics.csv
@@ -1,11 +1,11 @@
 model,approach,mae,mse,rmse,r2,total_time,anomesdia_datetime
-LinearRegression,Treino 5 K-folds,0.096,0.043,0.188,0.713,0.922,2021-04-21 20:59:16.814030
-LinearRegression,Validation set,0.092,0.019,0.139,0.896,0.002,2021-04-21 20:59:16.814030
-DecisionTreeRegressor,Treino 5 K-folds,0.152,0.047,0.216,0.686,0.486,2021-04-21 20:59:16.814030
-DecisionTreeRegressor,Validation set,0.147,0.042,0.206,0.773,0.001,2021-04-21 20:59:16.814030
-Lasso,Treino 5 K-folds,0.189,0.065,0.254,0.572,0.213,2021-04-21 20:59:16.814030
-Lasso,Validation set,0.201,0.08,0.283,0.569,0.003,2021-04-21 20:59:16.814030
-Ridge,Treino 5 K-folds,0.091,0.02,0.14,0.871,0.244,2021-04-21 20:59:16.814030
-Ridge,Validation set,0.094,0.019,0.138,0.898,0.006,2021-04-21 20:59:16.814030
-ElasticNet,Treino 5 K-folds,0.184,0.062,0.248,0.592,0.192,2021-04-21 20:59:16.814030
-ElasticNet,Validation set,0.194,0.074,0.272,0.604,0.006,2021-04-21 20:59:16.814030
+LinearRegression,Treino 5 K-folds,0.096,0.043,0.188,0.713,0.839,2021-05-10 23:14:37.989762
+LinearRegression,Validation set,0.092,0.019,0.139,0.896,0.008,2021-05-10 23:14:37.989762
+DecisionTreeRegressor,Treino 5 K-folds,0.152,0.047,0.216,0.686,0.468,2021-05-10 23:14:37.989762
+DecisionTreeRegressor,Validation set,0.147,0.042,0.206,0.773,0.001,2021-05-10 23:14:37.989762
+Lasso,Treino 5 K-folds,0.189,0.065,0.254,0.572,0.19,2021-05-10 23:14:37.989762
+Lasso,Validation set,0.201,0.08,0.283,0.569,0.019,2021-05-10 23:14:37.989762
+Ridge,Treino 5 K-folds,0.091,0.02,0.14,0.871,0.285,2021-05-10 23:14:37.989762
+Ridge,Validation set,0.094,0.019,0.138,0.898,0.01,2021-05-10 23:14:37.989762
+ElasticNet,Treino 5 K-folds,0.184,0.062,0.248,0.592,0.298,2021-05-10 23:14:37.989762
+ElasticNet,Validation set,0.194,0.074,0.272,0.604,0.013,2021-05-10 23:14:37.989762
diff --git a/examples/linear_regression/output/metrics/top_features.csv b/examples/linear_regression/output/metrics/top_features.csv
diff --git a/examples/linear_regression/output/models/decisiontreeregressor_20210510.pkl b/examples/linear_regression/output/models/decisiontreeregressor_20210510.pkl
diff --git a/examples/linear_regression/output/models/elasticnet_20210510.pkl b/examples/linear_regression/output/models/elasticnet_20210510.pkl
diff --git a/examples/linear_regression/output/models/lasso_20210510.pkl b/examples/linear_regression/output/models/lasso_20210510.pkl
diff --git a/examples/linear_regression/output/models/linearregression_20210510.pkl b/examples/linear_regression/output/models/linearregression_20210510.pkl
diff --git a/examples/linear_regression/output/models/ridge_20210510.pkl b/examples/linear_regression/output/models/ridge_20210510.pkl
diff --git a/examples/multiclass_classifier/output/imgs/confusion_matrix.png b/examples/multiclass_classifier/output/imgs/confusion_matrix.png
diff --git a/examples/multiclass_classifier/output/models/decisiontreeclassifier_20210417.pkl b/examples/multiclass_classifier/output/models/decisiontreeclassifier_20210417.pkl
diff --git a/examples/multiclass_classifier/output/models/decisiontreeclassifier_20210421.pkl b/examples/multiclass_classifier/output/models/decisiontreeclassifier_20210421.pkl
diff --git a/examples/multiclass_classifier/output/models/decisiontreeclassifier_20210510.pkl b/examples/multiclass_classifier/output/models/decisiontreeclassifier_20210510.pkl
diff --git a/examples/multiclass_classifier/output/models/randomforestclassifier_20210417.pkl b/examples/multiclass_classifier/output/models/randomforestclassifier_20210417.pkl
diff --git a/examples/multiclass_classifier/output/models/randomforestclassifier_20210421.pkl b/examples/multiclass_classifier/output/models/randomforestclassifier_20210421.pkl
diff --git a/examples/multiclass_classifier/output/models/randomforestclassifier_20210510.pkl b/examples/multiclass_classifier/output/models/randomforestclassifier_20210510.pkl
diff --git a/examples/multiclass_classifier/output/models/svc_20210417.pkl b/examples/multiclass_classifier/output/models/svc_20210417.pkl
diff --git a/examples/multiclass_classifier/output/models/svc_20210421.pkl b/examples/multiclass_classifier/output/models/svc_20210421.pkl
diff --git a/examples/multiclass_classifier/output/models/svc_20210510.pkl b/examples/multiclass_classifier/output/models/svc_20210510.pkl
diff --git a/mlcomposer/trainer.py b/mlcomposer/trainer.py
diff --git a/requirements.txt b/requirements.txt
@@ -4,23 +4,42 @@ cffi==1.14.5
 chardet==4.0.0
 colorama==0.4.4
 cryptography==3.4.7
+cycler==0.10.0
 docutils==0.17
 idna==2.10
 importlib-metadata==3.10.1
 jeepney==0.6.0
+joblib==0.14.1
 keyring==23.0.1
+kiwisolver==1.3.1
+llvmlite==0.36.0
+matplotlib==3.4.1
+-e git+https://github.com/ThiagoPanini/pylearn.git@913f7e6fe7069232cccb14fe7b1afcec1a2b1a3f#egg=mlcomposer
+numba==0.53.1
+numpy==1.18.5
 packaging==20.9
+pandas==1.1.5
+Pillow==8.2.0
 pkg-resources==0.0.0
 pkginfo==1.7.0
 pycparser==2.20
 Pygments==2.8.1
 pyparsing==2.4.7
+python-dateutil==2.8.1
+python-dotenv==0.17.0
+pytz==2021.1
 readme-renderer==29.0
 requests==2.25.1
 requests-toolbelt==0.9.1
 rfc3986==1.4.0
+scikit-learn==0.23.2
+scipy==1.6.2
+seaborn==0.10.0
 SecretStorage==3.3.1
+shap==0.37.0
 six==1.15.0
+slicer==0.0.3
+threadpoolctl==2.1.0
 tqdm==4.60.0
 twine==3.4.1
 urllib3==1.26.4

diff --git a/setup.py b/setup.py
@@ -37,7 +37,7 @@
 # Criando setup
 setup(
     name='mlcomposer',
-    version='0.0.11',
+    version='0.1.0',
     author='Thiago Panini',
     author_email='thipanini94@gmail.com',
     packages=find_packages(),