Improving code style

Mathias Quillot
1 parent 9aec207cb0
Showing 1 changed file with 13 additions and 24 deletions Side-by-side Diff
bin/extract_vectors.py
@@ -7,6 +7,7 @@
 import os
 import numpy as np
 import argparse
+from data import read_file, index_by_id, write_line
  
 parser = argparse.ArgumentParser(description='Extract a subset of vectors')
 parser.add_argument('vectorsfile', type=str,
  
@@ -25,28 +26,16 @@
 OUTPUT_FILE = args.output
  
 # READ VECTOR DATA
-data = {}
-data["en-us"] = {}
-data["fr-fr"] = {}
-with open(VECTOR_FILE, "r") as f:
-	for i, line in enumerate(f):
-		if TOY_VERSION == True and i > 100:
-			break
-		spl_line = line.split(" ")
-		if(len(pvectors) == 0):
-			pvectors = np.empty((0, len(spl_line[1:])), np.float32)
-		spl_meta = spl_line.split(",")
-		lang = spl_meta[0]
-		iden = spl_meta[3]
-		data[lang][iden] = line	
+features = read_file(VECTOR_FILE)
+features_ind = index_by_id(features)
+lst = read_file(LIST_FILE)
  
-# READ LIST AND WRITE NEW FILE
-with open(LIST_FILE, "r") as f, open(OUTPUT_FILE, "w") as o:
-	for i, line in enumerate(LIST_FILE):
-		if TOY_VERSION == True and i > 100:
-			break
-		spl_meta = line.split(",")
-		lang = spl_meta[0]
-		iden = spl_meta[3]
-		OUTPUT_FILE.write(data[lang][iden])
+
+# COMPUTE KEPT FEATS
+kept_feats = [features_ind[x[0][0]][x[0][3]] for x in lst]
+
+# WRITE IN FILE
+with open(OUTPUT_FILE, 'w') as f:
+    for feat in kept_feats:
+        write_line(feat[0], feat[1], f=f)
...	...	@@ -7,6 +7,7 @@
7	7	import os
8	8	import numpy as np
9	9	import argparse
	10	+from data import read_file, index_by_id, write_line
10	11
11	12	parser = argparse.ArgumentParser(description='Extract a subset of vectors')
12	13	parser.add_argument('vectorsfile', type=str,
13	14
...	...	@@ -25,28 +26,16 @@
25	26	OUTPUT_FILE = args.output
26	27
27	28	# READ VECTOR DATA
28		-data = {}
29		-data["en-us"] = {}
30		-data["fr-fr"] = {}
31		-with open(VECTOR_FILE, "r") as f:
32		- for i, line in enumerate(f):
33		- if TOY_VERSION == True and i > 100:
34		- break
35		- spl_line = line.split(" ")
36		- if(len(pvectors) == 0):
37		- pvectors = np.empty((0, len(spl_line[1:])), np.float32)
38		- spl_meta = spl_line.split(",")
39		- lang = spl_meta[0]
40		- iden = spl_meta[3]
41		- data[lang][iden] = line
	29	+features = read_file(VECTOR_FILE)
	30	+features_ind = index_by_id(features)
	31	+lst = read_file(LIST_FILE)
42	32
43		-# READ LIST AND WRITE NEW FILE
44		-with open(LIST_FILE, "r") as f, open(OUTPUT_FILE, "w") as o:
45		- for i, line in enumerate(LIST_FILE):
46		- if TOY_VERSION == True and i > 100:
47		- break
48		- spl_meta = line.split(",")
49		- lang = spl_meta[0]
50		- iden = spl_meta[3]
51		- OUTPUT_FILE.write(data[lang][iden])
	33	+
	34	+# COMPUTE KEPT FEATS
	35	+kept_feats = [features_ind[x[0][0]][x[0][3]] for x in lst]
	36	+
	37	+# WRITE IN FILE
	38	+with open(OUTPUT_FILE, 'w') as f:
	39	+ for feat in kept_feats:
	40	+ write_line(feat[0], feat[1], f=f)