diff simple_model_fit.py @ 29:95d0f81e46e8 draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit eb703290e2589561ea215c84aa9f71bcfe1712c6"
author bgruening
date Fri, 01 Nov 2019 17:14:31 -0400
parents
children 18b39ada6f35
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/simple_model_fit.py	Fri Nov 01 17:14:31 2019 -0400
@@ -0,0 +1,145 @@
+import argparse
+import json
+import pandas as pd
+import pickle
+
+from galaxy_ml.utils import load_model, read_columns
+from sklearn.pipeline import Pipeline
+
+
+def _get_X_y(params, infile1, infile2):
+    """ read from inputs and output X and y
+
+    Parameters
+    ----------
+    params : dict
+        Tool inputs parameter
+    infile1 : str
+        File path to dataset containing features
+    infile2 : str
+        File path to dataset containing target values
+
+    """
+    # store read dataframe object
+    loaded_df = {}
+
+    input_type = params['input_options']['selected_input']
+    # tabular input
+    if input_type == 'tabular':
+        header = 'infer' if params['input_options']['header1'] else None
+        column_option = (params['input_options']['column_selector_options_1']
+                         ['selected_column_selector_option'])
+        if column_option in ['by_index_number', 'all_but_by_index_number',
+                             'by_header_name', 'all_but_by_header_name']:
+            c = params['input_options']['column_selector_options_1']['col1']
+        else:
+            c = None
+
+        df_key = infile1 + repr(header)
+        df = pd.read_csv(infile1, sep='\t', header=header,
+                         parse_dates=True)
+        loaded_df[df_key] = df
+
+        X = read_columns(df, c=c, c_option=column_option).astype(float)
+    # sparse input
+    elif input_type == 'sparse':
+        X = mmread(open(infile1, 'r'))
+
+    # Get target y
+    header = 'infer' if params['input_options']['header2'] else None
+    column_option = (params['input_options']['column_selector_options_2']
+                     ['selected_column_selector_option2'])
+    if column_option in ['by_index_number', 'all_but_by_index_number',
+                         'by_header_name', 'all_but_by_header_name']:
+        c = params['input_options']['column_selector_options_2']['col2']
+    else:
+        c = None
+
+    df_key = infile2 + repr(header)
+    if df_key in loaded_df:
+        infile2 = loaded_df[df_key]
+    else:
+        infile2 = pd.read_csv(infile2, sep='\t',
+                              header=header, parse_dates=True)
+        loaded_df[df_key] = infile2
+
+    y = read_columns(
+            infile2,
+            c=c,
+            c_option=column_option,
+            sep='\t',
+            header=header,
+            parse_dates=True)
+    if len(y.shape) == 2 and y.shape[1] == 1:
+        y = y.ravel()
+
+    return X, y
+
+
+def main(inputs, infile_estimator, infile1, infile2, out_object,
+         out_weights=None):
+    """ main
+
+    Parameters
+    ----------
+    inputs : str
+        File path to galaxy tool parameter
+
+    infile_estimator : str
+        File paths of input estimator
+
+    infile1 : str
+        File path to dataset containing features
+
+    infile2 : str
+        File path to dataset containing target labels
+
+    out_object : str
+        File path for output of fitted model or skeleton
+
+    out_weights : str
+        File path for output of weights
+
+    """
+    with open(inputs, 'r') as param_handler:
+        params = json.load(param_handler)
+
+    # load model
+    with open(infile_estimator, 'rb') as est_handler:
+        estimator = load_model(est_handler)
+
+    X_train, y_train = _get_X_y(params, infile1, infile2)
+
+    estimator.fit(X_train, y_train)
+    
+    main_est = estimator
+    if isinstance(main_est, Pipeline):
+        main_est = main_est.steps[-1][-1]
+    if hasattr(main_est, 'model_') \
+            and hasattr(main_est, 'save_weights'):
+        if out_weights:
+            main_est.save_weights(out_weights)
+        del main_est.model_
+        del main_est.fit_params
+        del main_est.model_class_
+        del main_est.validation_data
+        if getattr(main_est, 'data_generator_', None):
+            del main_est.data_generator_
+
+    with open(out_object, 'wb') as output_handler:
+        pickle.dump(estimator, output_handler,
+                    pickle.HIGHEST_PROTOCOL)
+
+
+if __name__ == '__main__':
+    aparser = argparse.ArgumentParser()
+    aparser.add_argument("-i", "--inputs", dest="inputs", required=True)
+    aparser.add_argument("-X", "--infile_estimator", dest="infile_estimator")
+    aparser.add_argument("-y", "--infile1", dest="infile1")
+    aparser.add_argument("-g", "--infile2", dest="infile2")
+    aparser.add_argument("-o", "--out_object", dest="out_object")
+    aparser.add_argument("-t", "--out_weights", dest="out_weights")
+    args = aparser.parse_args()
+
+    main(args.inputs, args.infile_estimator, args.infile1,
+         args.infile2, args.out_object, args.out_weights)