Deep Learning Workshop

@@ -77,18 +77,32 @@ if __name__ == "__main__":
         sequences = df_filtered['sequence']
         labels = df_filtered['label']
 
+    count_exon = 0
+    count_utr = 0
+    total_exon_length = 0
+    total_utr_length = 0
     max_exon_length = 0
     max_utr_length = 0
     # Getting the max length of sequences
     for sequence, label in zip(sequences, labels):
         if label == "exon":
+            count_exon += 1
+            total_exon_length += total_exon_length
             if len(sequence) > max_exon_length:
                 max_exon_length = len(sequence)
         elif label == "utr":
+            count_utr += 1
+            total_utr_length += total_utr_length
             if len(sequence) > max_utr_length:
                 max_utr_length = len(sequence)
     print("Max exon length: {}".format(max_exon_length))
     print("Max utr length: {}".format(max_utr_length))
+    print("Count exon: {}".format(count_exon))
+    print("Count utr: {}".format(count_utr))
+    print("Total exon length: {}".format(total_exon_length))
+    print("Total utr length: {}".format(total_utr_length))
+
+    quit()
 
     if max_exon_length > max_utr_length:
         max_length = max_exon_length
@@ -108,9 +122,9 @@ if __name__ == "__main__":
         else:
             sequence_adjust = sequence + 'ACGTX'
         sequences_adjust.append(sequence_adjust)
-        print("Length sequence_adjust: {}".format(len(sequence_adjust)))
+        # print("Length sequence_adjust: {}".format(len(sequence_adjust)))
         integer_encoded = integer_encoder.fit_transform(list(sequence_adjust))
-        print("integer_encoded.classes_: {}".format(integer_encoder.classes_))
+        # print("integer_encoded.classes_: {}".format(integer_encoder.classes_))
         integer_encoded = np.array(integer_encoded).reshape(-1, 1)
         # print("integer_encoded: {}".format(integer_encoded))
         one_hot_encoded = one_hot_encoder.fit_transform(integer_encoded)