Merge branch 'master' of https://git.wmi.amu.edu.pl/s470611/challenging-america-word-gap-prediction

run.py

@@ -1,19 +1,10 @@
+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
 
-
-def clean(text):
-    text = str(text).lower().replace("-\\n", "").replace("\\n", " ")
-    return re.sub(r"\p{P}", "", text)
-
-
-class Collection:
-    def __init__(self, path: str) -> None:
-        self._path = path
-
     def read(self):
         self.data = pd.read_csv(
             self._path,
@@ -25,7 +16,7 @@ class Collection:
 
 
 class Model:
-    def __init__(self, alpha: float = 0.01) -> None:
+    def __init__(self, alpha):
         self.alpha = alpha
         self.model = defaultdict(lambda: defaultdict(lambda: 0))
         self.vocab = set()
@@ -33,12 +24,12 @@ class Model:
     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:
-                self.model[w1][w2] += 1
-                self.vocab.add(w1)
-                self.vocab.add(w2)
-
+            for w1, w2 in bigrams(words, pad_left=True, pad_right=True):
+                if w1 and w2:
+                    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)
@@ -46,6 +37,7 @@ class Model:
                 nominator = self.model[w1][w2] + self.alpha
                 self.model[w1][w2] = nominator / denominator
 
+
     def _predict(self, word):
         predictions = dict(self.model[word])
         most_common = dict(Counter(predictions).most_common(6))
@@ -67,7 +59,11 @@ class Model:
 
         return str_prediction
 
-    def _save(self, save_path: str, data):
+
+    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
+        )
         with open(save_path, "w") as file:
             for _, row in data.iterrows():
                 words = word_tokenize(clean(row[6]))
@@ -77,30 +73,30 @@ class Model:
                     prediction = self._predict(words[-1])
                 file.write(prediction + "\n")
 
-    def predict(self, read_path: str, save_path: str):
-        collection = Collection(read_path)
-        collection.read()
-        self._save(save_path, collection.data)
-
-
 
 if __name__ == '__main__':
 
-    data = Collection("train/in.tsv.xz")
-    data.read()
+    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_labels = Collection("train/expected.tsv")
-    train_labels.read()
-
-
-    train_data = data.data[[6, 7]]
-    train_data = pd.concat([train_data, train_labels.data], axis=1)
+    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()
+    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")
+    model.predict("test-A/in.tsv.xz", "test-A/out.tsv")