[s9] bug fixes -- wrongly pick from step7

s9.py

@@ -8,12 +8,15 @@ from base import create_csv, TARGET_DIR, MODEL_LIST, RAW_DIR
 import os
 import csv
 import re
+import sys
 
 FN_CONST = 19
 
-def get_retrieved_yynn_count(model):
+
+def get_retrieved_yynn_count(model, **kwargs):
     result = {}
-    for i in '1234':
+    order = kwargs.get('order', '1234')
+    for i in order:
         P = os.path.join(TARGET_DIR, 'part7', '%s-%s.csv' % (model, i))
         with open(P, 'rb') as f:
             rows = csv.reader(f)
@@ -34,11 +37,13 @@ def process_file(seven_data, data, header):
     for i in xrange(start_ind, len(data)):
         R_id = header[i]
         if R_id not in seven_data:
-            print("%s missing in step7" % R_id)
             continue
         TP = float(data[i])
         FP = float(seven_data[R_id]) - TP
         FN = float(FN_CONST) - TP
+        # print(data[0])
+        # print(seven_data)
+        # print('FP = %s - %s = %s' % (seven_data[R_id], TP, FP))
         # print('TP: %s, FP: %s, FN: %s' % (TP, FP, FN))
 
         P = (TP / (TP + FP)) * 100
@@ -47,7 +52,8 @@ def process_file(seven_data, data, header):
             F = 2 * (P * R) / (P + R)
         except ZeroDivisionError:
             F = 'inf'
-            print('ZeroDivisionError\n    %s -- R_id: %s | P: %s | R: %s' % (data[0], R_id, P, R))
+            # print('\nZeroDivisionError: '
+            #       '%s -- R_id: %s | P: %s | R: %s' % (data[0], R_id, P, R), end='')
 
         prf_output.append({
             'R_id': R_id,
@@ -63,10 +69,16 @@ def loop_thru_step8():
     BASE_PATH = os.path.join(TARGET_DIR, 'part8')
     for i in os.walk(BASE_PATH):
         for j in i[2]:
+            print('\r >> processing %s                ' % j, end='')
+            sys.stdout.flush()
             output = []
-            seven = get_retrieved_yynn_count(j[:4])
+            '''
+            Nah, getting wrong data from step 7
+            '''
+            _m = j[:4]
+            _o = j[5]
+            seven = get_retrieved_yynn_count(_m, **{'order': _o})
             fpath = os.path.join(BASE_PATH, j)
-            # print(fpath)
             with open(fpath, 'rb') as f:
                 output_header = ['lo_id', j[:4]]
                 output_sub_header = ['', '', ]
@@ -88,5 +100,8 @@ def loop_thru_step8():
             result = [output_header] + [output_sub_header] + output
             create_csv(output_name, result, directory='part9')
             is_header_created = False
+            print('\r >> done %s                    ' % j, end='')
+            sys.stdout.flush()
+    print('')
 
 loop_thru_step8()