Fixed problem with code

code.py

@@ -9,7 +9,7 @@ from spacy.lang.en import English
 
 def create_train(input,output1,output0):
     create_dictionary = pd.read_csv(input, delimiter="\t", header=None, names=["num","txt"], error_bad_lines=False, skip_blank_lines=False)
-    create_dictionary = create_dictionary[:200000]
+    create_dictionary = create_dictionary[:900000]
     values_1 = (create_dictionary['txt'].where(create_dictionary['num']==1)).dropna()
     values_0 = (create_dictionary['txt'].where(create_dictionary['num']==0)).dropna()
     values_1.to_csv(output1,header=None, index=None)

read_results.py

@@ -4,12 +4,12 @@ import pandas as pd
 def read_file(input_file):
     create_file = pd.read_csv(input_file, delimiter=" ", header=None, names=["%%", "Nw","PP","PPwp","Nbo","Noov","OOV"], error_bad_lines=True,
                               skip_blank_lines=True)
-    create_file = create_file[:200000]
+    create_file = create_file[:900000]
     return create_file
 
 def check_results(input_negative,input_positive,output):
     f = open(output,"w")
-    for i,j in zip(input_negative,input_positive):
+    for i,j in zip(input_negative[:-1],input_positive[:-1]):
         if (i>j):
             f.write("0.3\n")
         else:
@@ -22,9 +22,9 @@ def replacer(input_file_negativ,input_file_positive):
     out_p = read_file(input_file_positive)
     # --- Replace prefixes using str.replace ---- #
     out_n_sent_nw = out_n['PP'].str.replace('sent_PP=', "")
-    out_n_sent_nw = out_n_sent_nw.str.replace('PP=', "")
+    #out_n_sent_nw = out_n_sent_nw.str.replace('PP=', "")
     out_p_sent_nw = out_p['PP'].str.replace('sent_PP=', "")
-    out_p_sent_nw = out_p_sent_nw.str.replace('PP=', "")
+    #out_p_sent_nw = out_p_sent_nw.str.replace('PP=', "")
 
     return out_n_sent_nw,out_p_sent_nw