3

run.py

@@ -12,7 +12,6 @@ data = pd.read_csv(
     error_bad_lines=False,
     header=None,
     quoting=csv.QUOTE_NONE,
-    nrows=250000
 )
 train_labels = pd.read_csv(
     "train/expected.tsv",
@@ -20,7 +19,6 @@ train_labels = pd.read_csv(
     error_bad_lines=False,
     header=None,
     quoting=csv.QUOTE_NONE,
-    nrows=250000
 )
 
 train_data = data[[6, 7]]
@@ -33,22 +31,17 @@ model = defaultdict(lambda: defaultdict(lambda: 0))
 
 def clean(text):
     text = str(text)
-        # normalize text
     text = (
-        unicodedata.normalize('NFKD', text).encode('ascii', 'ignore').decode(
+        unicodedata.normalize("NFKD", text)
-            'utf-8', 'ignore'))
+        .encode("ascii", "ignore")
-    # replace html chars with ' '
+        .decode("utf-8", "ignore")
-    text = re.sub('<.*?>', ' ', text)
+    )
-    # remove punctuation
+    text = re.sub("<.*?>", " ", text)
-    text = text.translate(str.maketrans(' ', ' ', string.punctuation))
+    text = text.translate(str.maketrans(" ", " ", string.punctuation))
-    # only alphabets and numerics
+    text = re.sub("[^a-zA-Z]", " ", text)
-    text = re.sub('[^a-zA-Z]', ' ', text)
-    # replace newline with space
     text = re.sub("\n", " ", text)
-    # lower case
     text = text.lower()
-    # split and join the words
+    text = " ".join(text.split())
-    text = ' '.join(text.split())
     return text