New implementation of data functions for skyrim

Mathias Quillot
1 parent a7fec48aaf
Showing 1 changed file with 48 additions and 0 deletions Side-by-side Diff
bin/data.py
@@ -10,6 +10,7 @@
  
 import sys
  
+
 def read_file(filepath):
     '''
     Read the file and return an array with pairs
@@ -26,6 +27,24 @@
     return data
  
  
+def read_file_skyrim(filepath):
+    '''
+    Read the file and return an array with pairs
+    where each pair is composed by the metas and the 
+    features.
+
+    This is for Skyrim files.
+    '''
+    data = []
+    with open(filepath, "r") as f:
+        for line in f:
+            splited = line.replace("\n", "").split(" ")
+            metas = splited[0].split(".")
+            features = splited[1:]
+            data.append((metas, features))
+    return data
+
+
 def index_by(data, num_col):
     '''
     Allows the user to index data by number of columns.
@@ -58,6 +77,24 @@
     return indexed
  
  
+def index_by_id_skyrim(data):
+    '''
+    Allows the user to index data by id.
+    Index data by id consists in indexing two times 
+    because data have two keys. On with the language 
+    and the other one with the id of the sentence.
+    '''
+    indexed = {}
+    for line in data:
+        metas = line[0]
+        id_sen = metas[2]
+        lang = metas[0]
+        if lang not in indexed:
+            indexed[lang] = {}
+        indexed[lang][id_sen] = line
+    return indexed
+
+
 def write_line(metas, features, f=sys.stdout):
     '''
     Just print the line. No need to specify a file.
@@ -67,4 +104,15 @@
     f: file to write it
     '''
     print(",".join(metas) + " " + " ".join(features), file=f)
+
+
+def write_line_skyrim(metas, features, f=sys.stdout):
+    '''
+    Just print the line. No need to specify a file.
+
+    metas: meta information on list
+    features: feature vector
+    f: file to write it
+    '''
+    print(".".join(metas) + " " + " ".join(features), file=f)
...	...	@@ -10,6 +10,7 @@
10	10
11	11	import sys
12	12
	13	+
13	14	def read_file(filepath):
14	15	'''
15	16	Read the file and return an array with pairs
...	...	@@ -26,6 +27,24 @@
26	27	return data
27	28
28	29
	30	+def read_file_skyrim(filepath):
	31	+ '''
	32	+ Read the file and return an array with pairs
	33	+ where each pair is composed by the metas and the
	34	+ features.
	35	+
	36	+ This is for Skyrim files.
	37	+ '''
	38	+ data = []
	39	+ with open(filepath, "r") as f:
	40	+ for line in f:
	41	+ splited = line.replace("\n", "").split(" ")
	42	+ metas = splited[0].split(".")
	43	+ features = splited[1:]
	44	+ data.append((metas, features))
	45	+ return data
	46	+
	47	+
29	48	def index_by(data, num_col):
30	49	'''
31	50	Allows the user to index data by number of columns.
...	...	@@ -58,6 +77,24 @@
58	77	return indexed
59	78
60	79
	80	+def index_by_id_skyrim(data):
	81	+ '''
	82	+ Allows the user to index data by id.
	83	+ Index data by id consists in indexing two times
	84	+ because data have two keys. On with the language
	85	+ and the other one with the id of the sentence.
	86	+ '''
	87	+ indexed = {}
	88	+ for line in data:
	89	+ metas = line[0]
	90	+ id_sen = metas[2]
	91	+ lang = metas[0]
	92	+ if lang not in indexed:
	93	+ indexed[lang] = {}
	94	+ indexed[lang][id_sen] = line
	95	+ return indexed
	96	+
	97	+
61	98	def write_line(metas, features, f=sys.stdout):
62	99	'''
63	100	Just print the line. No need to specify a file.
...	...	@@ -67,4 +104,15 @@
67	104	f: file to write it
68	105	'''
69	106	print(",".join(metas) + " " + " ".join(features), file=f)
	107	+
	108	+
	109	+def write_line_skyrim(metas, features, f=sys.stdout):
	110	+ '''
	111	+ Just print the line. No need to specify a file.
	112	+
	113	+ metas: meta information on list
	114	+ features: feature vector
	115	+ f: file to write it
	116	+ '''
	117	+ print(".".join(metas) + " " + " ".join(features), file=f)