smoothing fix

run.py

@@ -1,53 +1,41 @@
+from ast import Mod
 import pandas as pd
 import csv
 import regex as re
 from nltk import bigrams, word_tokenize
 from collections import Counter, defaultdict
-import string
-import unicodedata
-
-data = pd.read_csv(
-    "train/in.tsv.xz",
-    sep="\t",
-    error_bad_lines=False,
-    header=None,
-    quoting=csv.QUOTE_NONE,
-)
-train_labels = pd.read_csv(
-    "train/expected.tsv",
-    sep="\t",
-    error_bad_lines=False,
-    header=None,
-    quoting=csv.QUOTE_NONE,
-)
-
-train_data = data[[6, 7]]
-train_data = pd.concat([train_data, train_labels], axis=1)
-
-train_data["final"] = train_data[6] + train_data[0] + train_data[7]
-
-model = defaultdict(lambda: defaultdict(lambda: 0))
 
 
 def clean(text):
     text = str(text).lower().replace("-\\n", "").replace("\\n", " ")
     return re.sub(r"\p{P}", "", text)
 
-def train_model(data):
+class Model:
+    def __init__(self, alpha):
+        self.alpha = alpha
+        self.model = defaultdict(lambda: defaultdict(lambda: 0))
+        self.vocab = set()
+
+    def train(self, data):
         for _, row in data.iterrows():
             words = word_tokenize(clean(row["final"]))
             for w1, w2 in bigrams(words, pad_left=True, pad_right=True):
                 if w1 and w2:
-                model[w1][w2] += 1
-    for w1 in model:
-        total_count = float(sum(model[w1].values()))
-        for w2 in model[w1]:
-            model[w1][w2] /= total_count
+                    self.model[w1][w2] += 1
+                    self.vocab.add(w1)
+                    self.vocab.add(w2)
+                    
+        for w1 in self.model:
+            total_count = float(sum(self.model[w1].values()))
+            denominator = total_count + self.alpha * len(self.vocab)
+            for w2 in self.model[w1]:
+                nominator = self.model[w1][w2] + self.alpha
+                self.model[w1][w2] = nominator / denominator
 
 
-def predict(word):
-    predictions = dict(model[word])
-    most_common = dict(Counter(predictions).most_common(5))
+    def _predict(self, word):
+        predictions = dict(self.model[word])
+        most_common = dict(Counter(predictions).most_common(6))
 
         total_prob = 0.0
         str_prediction = ""
@@ -67,7 +55,7 @@ def predict(word):
         return str_prediction
 
 
-def predict_data(read_path, save_path):
+    def predict(self, read_path, save_path):
         data = pd.read_csv(
             read_path, sep="\t", error_bad_lines=False, header=None, quoting=csv.QUOTE_NONE
         )
@@ -77,10 +65,33 @@ def predict_data(read_path, save_path):
                 if len(words) < 3:
                     prediction = "the:0.2 be:0.2 to:0.2 of:0.1 and:0.1 a:0.1 :0.1"
                 else:
-                prediction = predict(words[-1])
+                    prediction = self._predict(words[-1])
                 file.write(prediction + "\n")
 
 
-train_model(train_data)
-predict_data("dev-0/in.tsv.xz", "dev-0/out.tsv")
-predict_data("test-A/in.tsv.xz", "test-A/out.tsv")
+if __name__ == '__main__':
+
+    data = pd.read_csv(
+        "train/in.tsv.xz",
+        sep="\t",
+        error_bad_lines=False,
+        header=None,
+        quoting=csv.QUOTE_NONE,
+    )
+    train_labels = pd.read_csv(
+        "train/expected.tsv",
+        sep="\t",
+        error_bad_lines=False,
+        header=None,
+        quoting=csv.QUOTE_NONE,
+    )
+
+    train_data = data[[6, 7]]
+    train_data = pd.concat([train_data, train_labels], axis=1)
+
+    train_data["final"] = train_data[6] + train_data[0] + train_data[7]
+
+    model = Model(0.0001)
+    model.train(train_data)
+    model.predict("dev-0/in.tsv.xz", "dev-0/out.tsv")
+    model.predict("test-A/in.tsv.xz", "test-A/out.tsv")