Deep Learning Workshop

@@ -62,18 +62,20 @@ if __name__ == "__main__":
     # each row corresponds to one possible value of each feature.
     # each row corresponds to one possible value of each feature.
     one_hot_encoder = OneHotEncoder(categories='auto')
     one_hot_encoder = OneHotEncoder(categories='auto')
     input_features = []
     input_features = []
-    sequences = []
 
 
     # Read file with sequences
     # Read file with sequences
     with open(os.path.join(args.inputPath, args.inputFile), mode="r") as tabfile:
     with open(os.path.join(args.inputPath, args.inputFile), mode="r") as tabfile:
         df = pd.read_csv(tabfile, delimiter='\t')
         df = pd.read_csv(tabfile, delimiter='\t')
-        print("df: {}".format(df))
-        sequences = df['sequence']
-        labels = df['label']
+        print("All rows in df: {}".format(len(df.index)))
+        df_filtered = df.loc[df['label'] in ["exon", "utr"]]
+        print("Only exon and utr rows in df: {}".format(len(df_filtered.index)))
+        # print("df: {}".format(df))
+        sequences = df_filtered['sequence']
+        labels = df_filtered['label']
 
 
     max_exon_length = 0
     max_exon_length = 0
     max_utr_length = 0
     max_utr_length = 0
-    # One-hot-encoding of sequences
+    # Getting the max length of sequences
     for sequence, label in zip(sequences, labels):
     for sequence, label in zip(sequences, labels):
         if label == "exon":
         if label == "exon":
             if len(sequence) > max_exon_length:
             if len(sequence) > max_exon_length:
@@ -81,17 +83,24 @@ if __name__ == "__main__":
         elif label == "utr":
         elif label == "utr":
             if len(sequence) > max_utr_length:
             if len(sequence) > max_utr_length:
                 max_utr_length = len(sequence)
                 max_utr_length = len(sequence)
-        '''
+    print("Max exon length: {}".format(max_exon_length))
+    print("Max utr length: {}".format(max_utr_length))
+
+    quit()
+
+    # Fill sequence with X char to get max length
+    # One-hot-encoding of sequences
+    for sequence, label in zip(sequences, labels):
+        if label == "exon":
+            if len(sequence) < max_exon_length:
+                sequence.ljust(max_exon_length + len(sequence), 'X')
+        elif label == "utr":
+            if len(sequence) < max_utr_length:
+                sequence.ljust(max_utr_length + len(sequence), 'X')
         integer_encoded = integer_encoder.fit_transform(list(sequence))
         integer_encoded = integer_encoder.fit_transform(list(sequence))
         integer_encoded = np.array(integer_encoded).reshape(-1, 1)
         integer_encoded = np.array(integer_encoded).reshape(-1, 1)
         one_hot_encoded = one_hot_encoder.fit_transform(integer_encoded)
         one_hot_encoded = one_hot_encoder.fit_transform(integer_encoded)
         input_features.append(one_hot_encoded.toarray())
         input_features.append(one_hot_encoded.toarray())
-        '''
-
-    print("Max exon length: {}".format(max_exon_length))
-    print("Max utr length: {}".format(max_utr_length))
-
-    exit()
 
 
     # Print first sequence and one-hot-encoding
     # Print first sequence and one-hot-encoding
     np.set_printoptions(threshold=40)
     np.set_printoptions(threshold=40)