Merge pull request #72 from bjherger/examples

Updated examples, major refactoring and feature improvements

README.md

@@ -188,7 +188,15 @@ board games with my partner in Seattle.
 
 ### Development
 
- - Adding CI/CD and PyPi links, and updating contact section w/ about the author (#70) 
+ - Adding CI/CD and PyPi links, and updating contact section w/ about the author (#70)
+ - Major rewrite / update of examples (#72)
+   - Fixes bug in embedding transformer. Embeddings will now be at least length 1. 
+   - Add functionality to check if `resp_var` is in the list of user provided variables
+   - Added better null filling w/ `CategoricalImputer`
+   - Added filling unseen values w/ `CategoricalImputer`
+   - Converted default transformer pipeline to use `copy.deepcopy` instead of `copy.copy`. This was a hotfix for a 
+   previously unknown issue. 
+   - Standardizing setting logging level, only in test base class and examples (when `__main__`)
 
 ### 1.3.5
 

examples/README.md

@@ -0,0 +1,5 @@
+# `keras-pandas` examples
+
+## Numerical response variable
+
+## Categorical response variable

examples/categorical_lending_club.py

@@ -0,0 +1,78 @@
+import logging
+
+import numpy
+import pandas
+from keras import Model
+from keras.layers import Dense
+from sklearn.model_selection import train_test_split
+
+from keras_pandas import lib
+from keras_pandas.Automater import Automater
+
+
+def main():
+
+    # Load data
+    observations = lib.load_lending_club()
+    # observations = lib.load_lending_club(test_run=False)
+    print('Observation columns: {}'.format(list(observations.columns)))
+    print('Class balance:\n {}'.format(observations['loan_status'].value_counts()))
+
+
+    # Heuristic data transformations
+    for var in ['int_rate', 'revol_util']:
+
+        # Strip out percent signs
+        observations[var] = observations[var].apply(lambda x: str(x).replace('%', ''))
+        observations[var] = pandas.to_numeric(observations[var], errors='coerce')
+    for var in ['mths_since_last_delinq', 'annual_inc_joint']:
+
+        # Heuristic null filling for some variables
+        observations[var] = observations[var].fillna(0)
+
+    # List out variable types
+    numerical_vars = ['loan_amnt', 'annual_inc', 'open_acc', 'dti', 'delinq_2yrs',
+                      'inq_last_6mths', 'mths_since_last_delinq', 'pub_rec', 'revol_bal', 'revol_util',
+                      'total_acc', 'pub_rec_bankruptcies']
+    categorical_vars = ['term', 'grade', 'emp_length', 'home_ownership', 'loan_status', 'addr_state',
+                        'application_type', 'disbursement_method']
+    text_vars = ['desc', 'purpose', 'title']
+
+    train_observations, test_observations = train_test_split(observations)
+    train_observations = train_observations.copy()
+    test_observations = test_observations.copy()
+
+    # Create and fit Automater
+    auto = Automater(numerical_vars=numerical_vars, categorical_vars=categorical_vars, text_vars=text_vars,
+                     response_var='loan_status')
+    auto.fit(train_observations)
+
+    # Create and fit keras (deep learning) model
+    # The auto.transform, auto.input_nub, auto.input_layers, and auto.loss are provided by keras-pandas, and
+    # everything else is core Keras
+    train_X, train_y = auto.transform(train_observations)
+    test_X, test_y = auto.transform(test_observations)
+
+    x = auto.input_nub
+    x = Dense(32)(x)
+    x = Dense(32, activation='relu')(x)
+    x = Dense(32)(x)
+    x = auto.output_nub(x)
+
+    model = Model(inputs=auto.input_layers, outputs=x)
+    model.compile(optimizer='Adam', loss=auto.loss, metrics=['accuracy'])
+
+    model.fit(train_X, train_y)
+
+    test_y_pred = model.predict(test_X)
+
+    # Inverse transform model output, to get usable results and save all results
+    test_observations[auto.response_var + '_pred'] = auto.inverse_transform_output(test_y_pred)
+    print('Predictions: {}'.format(test_observations[auto.response_var + '_pred']))
+
+    pass
+
+
+if __name__ == '__main__':
+    logging.getLogger().setLevel(logging.INFO)
+    main()

examples/categorical_mushrooms.py

@@ -0,0 +1,63 @@
+import logging
+
+import numpy
+import pandas
+from keras import Model
+from keras.layers import Dense
+from sklearn.model_selection import train_test_split
+
+from keras_pandas import lib
+from keras_pandas.Automater import Automater
+
+
+def main():
+
+    # Load data
+    observations = lib.load_mushroom()
+    # observations = lib.load_lending_club(test_run=False)
+    print('Observation columns: {}'.format(list(observations.columns)))
+    print('Class balance:\n {}'.format(observations['class'].value_counts()))
+
+    # List out variable types
+    numerical_vars = []
+    categorical_vars = ['class', 'cap-shape', 'cap-surface', 'cap-color', 'bruises', 'odor', 'gill-attachment', 'gill-spacing', 'gill-size', 'gill-color', 'stalk-shape', 'stalk-root', 'stalk-surface-above-ring', 'stalk-surface-below-ring', 'stalk-color-above-ring', 'stalk-color-below-ring', 'veil-type', 'veil-color', 'ring-number', 'ring-type', 'spore-print-color', 'population', 'habitat']
+    text_vars = []
+
+    train_observations, test_observations = train_test_split(observations)
+    train_observations = train_observations.copy()
+    test_observations = test_observations.copy()
+
+    # Create and fit Automater
+    auto = Automater(numerical_vars=numerical_vars, categorical_vars=categorical_vars, text_vars=text_vars,
+                     response_var='class')
+    auto.fit(train_observations)
+
+    # Create and fit keras (deep learning) model
+    # The auto.transform, auto.input_nub, auto.input_layers, and auto.loss are provided by keras-pandas, and
+    # everything else is core Keras
+    train_X, train_y = auto.transform(train_observations)
+    test_X, test_y = auto.transform(test_observations)
+
+    x = auto.input_nub
+    x = Dense(32)(x)
+    x = Dense(32, activation='relu')(x)
+    x = Dense(32)(x)
+    x = auto.output_nub(x)
+
+    model = Model(inputs=auto.input_layers, outputs=x)
+    model.compile(optimizer='Adam', loss=auto.loss, metrics=['accuracy'])
+
+    model.fit(train_X, train_y)
+
+    test_y_pred = model.predict(test_X)
+
+    # Inverse transform model output, to get usable results and save all results
+    test_observations[auto.response_var + '_pred'] = auto.inverse_transform_output(test_y_pred)
+    print('Predictions: {}'.format(test_observations[auto.response_var + '_pred']))
+
+    pass
+
+
+if __name__ == '__main__':
+    logging.getLogger().setLevel(logging.INFO)
+    main()

examples/categorical_titanic.py

@@ -0,0 +1,66 @@
+import logging
+
+import numpy
+import pandas
+from keras import Model
+from keras.layers import Dense
+from sklearn.model_selection import train_test_split
+
+from keras_pandas import lib
+from keras_pandas.Automater import Automater
+
+
+def main():
+
+    # Load data
+    observations = lib.load_titanic()
+    # observations = lib.load_lending_club(test_run=False)
+    print('Observation columns: {}'.format(list(observations.columns)))
+    print('Class balance:\n {}'.format(observations['survived'].value_counts()))
+
+    # List out variable types
+    numerical_vars = ['age', 'siblings_spouses_aboard', 'parents_children_aboard', 'fare']
+    categorical_vars = ['survived', 'pclass', 'sex']
+    text_vars = ['name']
+
+    for var in categorical_vars:
+        observations[var] = observations[var].astype(str)
+
+    train_observations, test_observations = train_test_split(observations)
+    train_observations = train_observations.copy()
+    test_observations = test_observations.copy()
+
+    # Create and fit Automater
+    auto = Automater(numerical_vars=numerical_vars, categorical_vars=categorical_vars, text_vars=text_vars,
+                     response_var='survived')
+    auto.fit(train_observations)
+
+    # Create and fit keras (deep learning) model
+    # The auto.transform, auto.input_nub, auto.input_layers, and auto.loss are provided by keras-pandas, and
+    # everything else is core Keras
+    train_X, train_y = auto.transform(train_observations)
+    test_X, test_y = auto.transform(test_observations)
+
+    x = auto.input_nub
+    x = Dense(32)(x)
+    x = Dense(32, activation='relu')(x)
+    x = Dense(32)(x)
+    x = auto.output_nub(x)
+
+    model = Model(inputs=auto.input_layers, outputs=x)
+    model.compile(optimizer='Adam', loss=auto.loss, metrics=['accuracy'])
+
+    model.fit(train_X, train_y)
+
+    test_y_pred = model.predict(test_X)
+
+    # Inverse transform model output, to get usable results and save all results
+    test_observations[auto.response_var + '_pred'] = auto.inverse_transform_output(test_y_pred)
+    print('Predictions: {}'.format(test_observations[auto.response_var + '_pred']))
+
+    pass
+
+
+if __name__ == '__main__':
+    logging.getLogger().setLevel(logging.INFO)
+    main()

examples/example_interface.py

@@ -0,0 +1,16 @@
+
+def main():
+    # TODO Load data
+    # TODO Heuristic data transformations
+    # TODO List out variable types
+    # TODO Create and fit Automater
+    # TODO Create and fit keras (deep learning) model.
+    # TODO List out which components are supplied by Automaterl
+    # TODO Inverse transform model output, to get usable results
+    # TODO Save all results
+
+    pass
+
+if __name__ == '__main__':
+    logging.getLogger().setLevel(logging.INFO)
+    main()