sport-text-classification s478874

run.py

@@ -0,0 +1,52 @@
+import pandas as pd
+from sklearn.naive_bayes import GaussianNB
+from sklearn.feature_extraction.text import TfidfVectorizer
+
+nrows = 10000
+
+
+def load_data(path):
+    try:
+        in_df = pd.read_csv(f'{path}/in.tsv', sep='\t', header=None, nrows=nrows, error_bad_lines=False)
+    except:
+        in_df = pd.read_csv(f'{path}/train.tsv', sep='\t', header=None, nrows=nrows, error_bad_lines=False)
+    try:
+        exp_df = pd.read_csv(f'{path}/expected.tsv', sep='\t', header=None, nrows=nrows, error_bad_lines=False)
+    except:
+        exp_df = None
+    return in_df, exp_df
+
+
+def write_res(data, path):
+    with open(path, 'w') as f:
+        for line in data:
+            f.write(f'{line}\n')
+    print(f"Data written {path}/out.tsv")
+
+
+
+
+def main():
+    in_df = load_data('train')
+    x_df, y_df = in_df[0][1], in_df[0][0]
+
+    vectorizer = TfidfVectorizer(lowercase=True, stop_words=['english'])
+    train_x = vectorizer.fit_transform(x_df)
+
+
+    gnb = GaussianNB()
+    gnb.fit(train_x.toarray(), y_df)
+
+    paths = ['dev-0', 'test-A']
+
+    for path in paths:
+        x = load_data(path)
+        vec = vectorizer.transform(x[0][0])
+    
+        result = gnb.predict(vec.todense())
+        write_res(result, f'{path}/out.tsv')
+
+
+
+if __name__ == '__main__':
+    main()