MCPcopy Index your code
hub / github.com/lazyprogrammer/machine_learning_examples / get_data

Function get_data

nlp_class2/pos_baseline.py:98–169  ·  view source on GitHub ↗
(split_sequences=False)

Source from the content-addressed store, hash-verified

96
97
98def get_data(split_sequences=False):
99 if not os.path.exists('chunking'):
100 print("Please create a folder in your local directory called 'chunking'")
101 print("train.txt and test.txt should be stored in there.")
102 print("Please check the comments to get the download link.")
103 exit()
104 elif not os.path.exists('chunking/train.txt'):
105 print("train.txt is not in chunking/train.txt")
106 print("Please check the comments to get the download link.")
107 exit()
108 elif not os.path.exists('chunking/test.txt'):
109 print("test.txt is not in chunking/test.txt")
110 print("Please check the comments to get the download link.")
111 exit()
112
113 word2idx = {}
114 tag2idx = {}
115 word_idx = 0
116 tag_idx = 0
117 Xtrain = []
118 Ytrain = []
119 currentX = []
120 currentY = []
121 for line in open('chunking/train.txt'):
122 line = line.rstrip()
123 if line:
124 r = line.split()
125 word, tag, _ = r
126 if word not in word2idx:
127 word2idx[word] = word_idx
128 word_idx += 1
129 currentX.append(word2idx[word])
130
131 if tag not in tag2idx:
132 tag2idx[tag] = tag_idx
133 tag_idx += 1
134 currentY.append(tag2idx[tag])
135 elif split_sequences:
136 Xtrain.append(currentX)
137 Ytrain.append(currentY)
138 currentX = []
139 currentY = []
140
141 if not split_sequences:
142 Xtrain = currentX
143 Ytrain = currentY
144
145 # load and score test data
146 Xtest = []
147 Ytest = []
148 currentX = []
149 currentY = []
150 for line in open('chunking/test.txt'):
151 line = line.rstrip()
152 if line:
153 r = line.split()
154 word, tag, _ = r
155 if word in word2idx:

Callers 5

pos_tf.pyFile · 0.90
ner_tf.pyFile · 0.90
mainFunction · 0.90
mainFunction · 0.90
mainFunction · 0.70

Calls

no outgoing calls

Tested by

no test coverage detected