434780

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/challenging-america-word-gap-prediction.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/challenging-america-word-gap-prediction.iml" filepath="$PROJECT_DIR$/.idea/challenging-america-word-gap-prediction.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

in-header.tsv

@@ -1 +1 @@
-FileId	Year	LeftContext	RightContext
+FileId	Year	LeftContext	RightContext

out-header.tsv

@@ -1 +1 @@
-Word
+Word

readme.md

@@ -1,9 +1,9 @@
-Challenging America word-gap prediction
+Challenging America word-gap prediction
-===================================
+===================================
-
+
-Guess a word in a gap.
+Guess a word in a gap.
-
+
-Evaluation metric
+Evaluation metric
------------------
+-----------------
-
+
-LikelihoodHashed is the metric
+LikelihoodHashed is the metric

run.py

@@ -1,80 +1,80 @@
-from nltk import trigrams, word_tokenize
+from nltk import trigrams, word_tokenize
-import pandas as pd
+import pandas as pd
-import csv
+import csv
-import regex as re
+import regex as re
-from collections import Counter, defaultdict
+from collections import Counter, defaultdict
-
+
-
+
-train_set = pd.read_csv(
+train_set = pd.read_csv(
-    'train/in.tsv.xz',
+    'train/in.tsv.xz',
-    sep='\t',
+    sep='\t',
-    on_bad_lines='skip',
+    on_bad_lines='skip',
-    header=None,
+    header=None,
-    uoting=csv.QUOTE_NONE,
+    quoting=csv.QUOTE_NONE,
-    nrows=50000)
+    nrows=50000)
-
+
-
+
-train_labels = pd.read_csv(
+train_labels = pd.read_csv(
-    'train/expected.tsv',
+    'train/expected.tsv',
-    sep='\t',
+    sep='\t',
-    on_bad_lines='skip',
+    on_bad_lines='skip',
-    header=None,
+    header=None,
-    quoting=csv.QUOTE_NONE,
+    quoting=csv.QUOTE_NONE,
-    nrows=50000)
+    nrows=50000)
-
+
-
+
-def data_preprocessing(text):
+def data_preprocessing(text):
-    return re.sub(r'\p{P}', '', text.lower().replace('-\\n', '').replace('\\n', ' '))
+    return re.sub(r'\p{P}', '', text.lower().replace('-\\n', '').replace('\\n', ' '))
-
+
-
+
-def predict(before, after):
+def predict(before, after):
-    prediction = dict(Counter(dict(trigram[before, after])).most_common(5))
+    prediction = dict(Counter(dict(trigram[before, after])).most_common(5))
-    result = ''
+    result = ''
-    prob = 0.0
+    prob = 0.0
-    for key, value in prediction.items():
+    for key, value in prediction.items():
-        prob += value
+        prob += value
-        result += f'{key}:{value} '
+        result += f'{key}:{value} '
-    if prob == 0.0:
+    if prob == 0.0:
-        return 'to:0.015 be:0.015 the:0.015 not:0.01 and:0.02 a:0.02 :0.9'
+        return 'to:0.015 be:0.015 the:0.015 not:0.01 and:0.02 a:0.02 :0.9'
-    result += f':{max(1 - prob, 0.01)}'
+    result += f':{max(1 - prob, 0.01)}'
-    return result
+    return result
-
+
-
+
-def make_prediction(file):
+def make_prediction(file):
-    data = pd.read_csv(f'{file}/in.tsv.xz', sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE)
+    data = pd.read_csv(f'{file}/in.tsv.xz', sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE)
-    with open(f'{file}/out.tsv', 'w', encoding='utf-8') as file_out:
+    with open(f'{file}/out.tsv', 'w', encoding='utf-8') as file_out:
-        for _, row in data.iterrows():
+        for _, row in data.iterrows():
-            before, after = word_tokenize(data_preprocessing(str(row[6]))), word_tokenize(data_preprocessing(str(row[7])))
+            before, after = word_tokenize(data_preprocessing(str(row[6]))), word_tokenize(data_preprocessing(str(row[7])))
-            if len(before) < 3 or len(after) < 3:
+            if len(before) < 3 or len(after) < 3:
-                prediction = 'to:0.015 be:0.015 the:0.015 not:0.01 and:0.02 a:0.02 :0.9'
+                prediction = 'to:0.015 be:0.015 the:0.015 not:0.01 and:0.02 a:0.02 :0.9'
-            else:
+            else:
-                prediction = predict(before[-1], after[0])
+                prediction = predict(before[-1], after[0])
-            file_out.write(prediction + '\n')
+            file_out.write(prediction + '\n')
-
+
-
+
-train_set = train_set[[6, 7]]
+train_set = train_set[[6, 7]]
-train_set = pd.concat([train_set, train_labels], axis=1)
+train_set = pd.concat([train_set, train_labels], axis=1)
-train_set['line'] = train_set[6] + train_set[0] + train_set[7]
+train_set['line'] = train_set[6] + train_set[0] + train_set[7]
-
+
-
+
-trigram = defaultdict(lambda: defaultdict(lambda: 0))
+trigram = defaultdict(lambda: defaultdict(lambda: 0))
-
+
-rows = train_set.iterrows()
+rows = train_set.iterrows()
-rows_len = len(train_set)
+rows_len = len(train_set)
-for index, (_, row) in enumerate(rows):
+for index, (_, row) in enumerate(rows):
-    text = data_preprocessing(str(row['line']))
+    text = data_preprocessing(str(row['line']))
-    words = word_tokenize(text)
+    words = word_tokenize(text)
-    for word_1, word_2, word_3 in trigrams(words, pad_right=True, pad_left=True):
+    for word_1, word_2, word_3 in trigrams(words, pad_right=True, pad_left=True):
-        if word_1 and word_2 and word_3:
+        if word_1 and word_2 and word_3:
-            trigram[(word_1, word_3)][word_2] += 1
+            trigram[(word_1, word_3)][word_2] += 1
-
+
-model_len = len(trigram)
+model_len = len(trigram)
-for index, words_1_3 in enumerate(trigram):
+for index, words_1_3 in enumerate(trigram):
-    count = sum(trigram[words_1_3].values())
+    count = sum(trigram[words_1_3].values())
-    for word_2 in trigram[words_1_3]:
+    for word_2 in trigram[words_1_3]:
-        trigram[words_1_3][word_2] += 0.25
+        trigram[words_1_3][word_2] += 0.25
-        trigram[words_1_3][word_2] /= float(count + 0.25 + len(word_2))
+        trigram[words_1_3][word_2] /= float(count + 0.25 + len(word_2))
-
+
-
+
-make_prediction('test-A')
+make_prediction('test-A')
-make_prediction('dev-0')
+make_prediction('dev-0')