Fix missing import and black formatting

sklearn_training.py

@@ -14,12 +14,12 @@ import bootstrapped.stats_functions as bs_stats
 import numpy as np
 import pandas as pd
 from mlpy import borda_count, canberra_stability
-from sklearn import preprocessing
+from sklearn import preprocessing, svm
 from sklearn.ensemble import RandomForestClassifier
-from sklearn import svm
-from sklearn.metrics import make_scorer, accuracy_score, matthews_corrcoef, roc_auc_score
-from sklearn.model_selection import (StratifiedKFold, StratifiedShuffleSplit,
-                                     train_test_split, GridSearchCV)
+from sklearn.metrics import (accuracy_score, make_scorer, matthews_corrcoef,
+                             roc_auc_score)
+from sklearn.model_selection import (GridSearchCV, StratifiedKFold,
+                                     StratifiedShuffleSplit, train_test_split)
 from sklearn.multiclass import OneVsRestClassifier
 from sklearn.pipeline import Pipeline
 

sklearn_validation.py

@@ -11,28 +11,34 @@ import sys
 
 import numpy as np
 import pandas as pd
-from sklearn.ensemble import RandomForestClassifier
-from sklearn import svm
-from sklearn.metrics import make_scorer, accuracy_score, matthews_corrcoef, roc_auc_score
-from sklearn.model_selection import StratifiedShuffleSplit, GridSearchCV
-from sklearn import preprocessing
+from sklearn import preprocessing, svm
+from sklearn.metrics import (accuracy_score, make_scorer, matthews_corrcoef,
+                             roc_auc_score)
+from sklearn.model_selection import GridSearchCV, StratifiedShuffleSplit
 from sklearn.pipeline import Pipeline
 
-import performance as perf
 from extract_topfeats import extract_feats
 from input_output import load_data
 
-parser = argparse.ArgumentParser(description='Run a validation experiment using LibLinear.')
-parser.add_argument('CONFIGFILE', type=str, help='Training experiment configuration file')
+parser = argparse.ArgumentParser(
+    description='Run a validation experiment using LibLinear.'
+)
+parser.add_argument(
+    'CONFIGFILE', type=str, help='Training experiment configuration file'
+)
 parser.add_argument('TSFILE', type=str, help='Validation datafile')
 parser.add_argument('OUTDIR', type=str, help='Output directory')
-parser.add_argument('--tslab', type=str, default=None, help='Validation labels, if available')
-parser.add_argument('--nf', type=int, default=None, help='Custom number of top features')
+parser.add_argument(
+    '--tslab', type=str, default=None, help='Validation labels, if available'
+)
+parser.add_argument(
+    '--nf', type=int, default=None, help='Custom number of top features'
+)
 
 __author__ = 'Marco Chierici, Alessandro Zandona'
 __date__ = '15 December 2016'
 
-if len(sys.argv)==1:
+if len(sys.argv) == 1:
     parser.print_help()
     sys.exit(1)
 
@@ -48,7 +54,7 @@ TUN_CV_K = 10
 # fraction of the dataset to keep apart as test split (for SVM tuning)
 TUN_CV_P = 0.5
 # list of parameters for LSVM tuning
-TUN_PARAMS_LSVM = [{'svm__C': [10**int(k) for k in np.arange(-2, 3)]}]
+TUN_PARAMS_LSVM = [{'svm__C': [10 ** int(k) for k in np.arange(-2, 3)]}]
 
 config = ConfigParser.RawConfigParser()
 config.read(CONFIGFILE)
@@ -80,12 +86,14 @@ le = preprocessing.LabelEncoder()
 sample_names_tr, var_names_tr, x_tr = load_data(TR_TOPFEATS)
 y_tr = pd.read_csv(LABELSFILE, sep='\t', header=None).values
 y_tr = le.fit_transform(y_tr)
+print(y_tr.shape)
 sample_names_ts, var_names_ts, x_ts = load_data(TS_TOPFEATS)
 # load the TS labels if available
 if TSLABELSFILE is not None:
-    y_ts = pd.read_csv(TSLABELSFILE, sep='\t', header=None).values
+    y_ts = pd.read_csv(TSLABELSFILE, sep='\t', header=None, dtype=str).values
     y_ts = le.transform(y_ts)
 
+
 # define classifier
 if MODEL_TYPE == "randomForest":
     model = RandomForestClassifier(n_estimators=500, criterion='gini', random_state=0)
@@ -94,15 +102,19 @@ elif MODEL_TYPE == "LSVM":
     if SCALING == 'std':
         scaler = preprocessing.StandardScaler()
     elif SCALING == 'minmax':
-        scaler = preprocessing.MinMaxScaler(feature_range=(-1,1))
+        scaler = preprocessing.MinMaxScaler(feature_range=(-1, 1))
     scorer = make_scorer(matthews_corrcoef)
     # tuning Pipeline
     tun_classif = svm.SVC(class_weight="balanced", kernel="linear")
     pipeline_steps = [('scaler', scaler), ('svm', tun_classif)]
     tuning_pipeline = Pipeline(pipeline_steps)
     # LSVM tuning
-    tuncv = StratifiedShuffleSplit(n_splits=TUN_CV_K, test_size=TUN_CV_P, random_state=0)
-    model = GridSearchCV(tuning_pipeline, param_grid=TUN_PARAMS_LSVM, cv=tuncv, scoring=scorer)
+    tuncv = StratifiedShuffleSplit(
+        n_splits=TUN_CV_K, test_size=TUN_CV_P, random_state=0
+    )
+    model = GridSearchCV(
+        tuning_pipeline, param_grid=TUN_PARAMS_LSVM, cv=tuncv, scoring=scorer
+    )
 
 # train
 model.fit(x_tr, y_tr)
@@ -138,17 +150,24 @@ with open(OUTFILE + "_TEST_pred_ts.txt", "w") as fout:
     for i in range(len(sample_names_ts)):
         fout.write("%s\t%s\n" % (sample_names_ts[i], p_ts_dec[i]))
 
-np.savetxt(OUTFILE + "_TEST_signature.txt",
-           np.array(var_names_tr).reshape(-1,1),
-           fmt='%s', delimiter='\t')
+np.savetxt(
+    OUTFILE + "_TEST_signature.txt",
+    np.array(var_names_tr).reshape(-1, 1),
+    fmt='%s',
+    delimiter='\t',
+)
 
 if MODEL_TYPE == "randomForest":
     with open(OUTFILE + "_TEST_prob_tr.txt", "w") as fout:
         fout.write("SAMPLE\tCLASS 0\tCLASS 1\n")
         for i in range(len(sample_names_tr)):
-            fout.write("%s\t%f\t%f\n" % (sample_names_tr[i], prob_tr[i,0], prob_tr[i,1]))
+            fout.write(
+                "%s\t%f\t%f\n" % (sample_names_tr[i], prob_tr[i, 0], prob_tr[i, 1])
+            )
 
     with open(OUTFILE + "_TEST_prob_ts.txt", "w") as fout:
         fout.write("SAMPLE\tCLASS 0\tCLASS 1\n")
         for i in range(len(sample_names_ts)):
-            fout.write("%s\t%f\t%f\n" % (sample_names_ts[i], prob_ts[i,0], prob_ts[i,1]))
+            fout.write(
+                "%s\t%f\t%f\n" % (sample_names_ts[i], prob_ts[i, 0], prob_ts[i, 1])
+            )