Merge pull request #79 from bjherger/ts_example

Timeseries example

examples/example_interface.py

@@ -2,10 +2,11 @@
 def main():
     # TODO Load data
     # TODO Heuristic data transformations
+    # TODO Train /test split
     # 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 List out which components are supplied by Automater
     # TODO Inverse transform model output, to get usable results
     # TODO Save all results
 

examples/numerical_lending_club.py → examples/numerical_response_lending_club.py

@@ -14,11 +14,9 @@ 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']:
 
@@ -38,6 +36,7 @@ def main():
                         'application_type', 'disbursement_method']
     text_vars = ['desc', 'purpose', 'title']
 
+    # Train /test split
     train_observations, test_observations = train_test_split(observations)
     train_observations = train_observations.copy()
     test_observations = test_observations.copy()

examples/numerical_response_stocks.py

@@ -0,0 +1,61 @@
+import logging
+
+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_instanbul_stocks(as_ts=True)
+    print('Observation columns: {}'.format(list(observations.columns)))
+
+    # Heuristic data transformations
+
+    # Train /test split
+    train_observations, test_observations = train_test_split(observations)
+    train_observations = train_observations.copy()
+    test_observations = test_observations.copy()
+
+    # List out variable types
+    timeseries_vars = ['ise_lagged', 'ise.1_lagged', 'sp_lagged', 'dax_lagged']
+    numerical_vars = ['ise']
+
+    # Create and fit Automater
+    auto = Automater(numerical_vars=numerical_vars, timeseries_vars=timeseries_vars,
+                     response_var='ise')
+    auto.fit(train_observations)
+
+    # Create and fit keras (deep learning) model.
+    # The auto.transform, auto.input_nub, auto.input_layers, auto.output_nub, and auto.loss are provided by
+    # keras-pandas, and everything else is core Keras
+
+    x = auto.input_nub
+    x = Dense(16)(x)
+    x = Dense(16, activation='relu')(x)
+    x = Dense(16)(x)
+    x = auto.output_nub(x)
+
+    model = Model(inputs=auto.input_layers, outputs=x)
+    model.compile(optimizer='adam', loss=auto.loss)
+
+    train_X, train_y = auto.transform(train_observations)
+    model.fit(train_X, train_y)
+
+    # Inverse transform model output, to get usable results
+    test_X, test_y = auto.transform(test_observations)
+    test_y_pred = model.predict(test_X)
+    test_observations[auto.response_var + '_pred'] = auto.inverse_transform_output(test_y_pred)
+    print('Predictions: {}'.format(test_observations[auto.response_var + '_pred']))
+
+    # TODO Save all results
+
+    pass
+
+
+if __name__ == '__main__':
+    logging.getLogger().setLevel(logging.INFO)
+    main()

tests/testexamples.py

@@ -1,22 +1,26 @@
-from examples import numerical_lending_club, categorical_lending_club, categorical_mushrooms, categorical_titanic
+from examples import numerical_response_lending_club, categorical_response_lending_club, categorical_response_mushrooms, \
+    categorical_response_titanic, numerical_response_stocks
 from tests.testbase import TestBase
 import numpy
 
 
 class TestExamples(TestBase):
     def test_numerical_lending_club(self):
         numpy.random.seed(0)
-        numerical_lending_club.main()
+        numerical_response_lending_club.main()
 
     def test_categorical_lending_club(self):
         numpy.random.seed(0)
-        categorical_lending_club.main()
+        categorical_response_lending_club.main()
 
     def test_categorical_mushrooms(self):
         numpy.random.seed(0)
-        categorical_mushrooms.main()
+        categorical_response_mushrooms.main()
 
     def test_categorical_titanic(self):
         numpy.random.seed(0)
-        categorical_titanic.main()
+        categorical_response_titanic.main()
 
+    def test_numerical_stocks(self):
+        numpy.random.seed(0)
+        numerical_response_stocks.main()