From ca0a2feda4d68967c7c6144e30fcc77a519894b3 Mon Sep 17 00:00:00 2001
From: Adrian Charkiewicz <adrcha2@st.amu.edu.pl>
Date: Wed, 26 Apr 2023 18:03:21 +0200
Subject: [PATCH] added trigram

---
 dev-0/lm0.py |  37 ------------------
 trigram.py   | 107 +++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 107 insertions(+), 37 deletions(-)
 delete mode 100644 dev-0/lm0.py
 create mode 100644 trigram.py

diff --git a/dev-0/lm0.py b/dev-0/lm0.py
deleted file mode 100644
index dd41624..0000000
--- a/dev-0/lm0.py
+++ /dev/null
@@ -1,37 +0,0 @@
-import torch
-from transformers import AutoTokenizer, AutoModelForMaskedLM
-import sys
-
-tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
-model = AutoModelForMaskedLM.from_pretrained("bert-base-uncased")
-
-for line in sys.stdin:
-    line_splitted = line.split("\t")
-    left_context = line_splitted[6].split(" ")[-1]
-    right_context = line_splitted[7].split(" ")[0]
-
-    word = "[MASK]"
-
-    text = f"{left_context} {word} {right_context}"
-
-    input_ids = tokenizer.encode(text, add_special_tokens=False, return_tensors="pt", max_length=512, truncation=True)
-
-    mask_token_index = torch.where(input_ids == tokenizer.mask_token_id)[1][0]
-
-    with torch.inference_mode():
-        outputs = model(input_ids)
-        predictions = outputs[0][0, mask_token_index].softmax(dim=0)
-
-    top_k = 500
-    top_k_tokens = torch.topk(predictions, top_k).indices.tolist()
-    result = ''
-    prob_sum = 0
-    for token in top_k_tokens:
-        word = tokenizer.convert_ids_to_tokens([token])[0]
-        prob = predictions[token].item()
-        prob_sum += prob 
-        result += f"{word}:{prob} "
-    diff = 1.0 - prob_sum
-    result += f":{diff}"
-    print(result)
-
diff --git a/trigram.py b/trigram.py
new file mode 100644
index 0000000..d181033
--- /dev/null
+++ b/trigram.py
@@ -0,0 +1,107 @@
+import csv
+import pandas as pd
+import regex as re
+import nltk
+import tqdm
+from nltk import trigrams, word_tokenize
+from collections import Counter, defaultdict
+import string 
+
+nltk.download("punkt")
+
+most_common_en_word = "the:0.3 be:0.2 to:0.15 of:0.1 and:0.025 a:0.0125 :0.2125"
+train_count = 150000
+# train set
+train_data = pd.read_csv("train/in.tsv.xz", sep="\t", on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE, nrows=train_count)
+
+# training labels
+train_labels = pd.read_csv("train/expected.tsv", sep="\t", on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE,nrows=train_count)
+
+dev_data = pd.read_csv("dev-0/in.tsv.xz", sep="\t", on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE)
+
+test_data = pd.read_csv("test-A/in.tsv.xz", sep="\t", on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE)
+
+def prepare_text(text):
+    text = text.lower().replace("-\\n", "").replace("\\n", " ")
+    text = re.sub(r"\p{P}", "", text)
+    return text
+
+def train_trigrams():
+    for _, row in tqdm.tqdm(train_data.iterrows()):
+        text = prepare_text(str(row["final"]))
+        words = word_tokenize(text)
+        for w1, w2, w3 in trigrams(words, pad_right=True, pad_left=True):
+            if all([w1, w2, w3]):
+                model[(w2, w3)][w1] += 1
+                model[(w1, w2)][w3] += 1
+
+    for w_pair in model:
+        ngram_count = float(sum(model[w_pair].values()))
+        for w3 in model[w_pair]:
+            model[w_pair][w3] /= ngram_count
+
+
+def predict_probs(word1, word2):
+    raw_prediction = dict(model[word1, word2])
+    prediction = dict(Counter(raw_prediction).most_common(6))
+
+    total_prob = 0.0
+    str_prediction = ""
+
+    for word, prob in prediction.items():
+        total_prob += prob
+        str_prediction += f"{word}:{prob} "
+
+    if total_prob == 0.0:
+        return most_common_en_word
+
+    remaining_prob = 1 - total_prob
+
+    if remaining_prob < 0.01:
+        remaining_prob = 0.01
+
+    str_prediction += f":{remaining_prob}"
+
+    return str_prediction
+
+
+def write_output():
+    with open("dev-0/out.tsv", "w") as file:
+        for _, row in dev_data.iterrows():
+            text = prepare_text(str(row[7]))
+            words = word_tokenize(text)
+            if len(words) < 3:
+                prediction = most_common_en_word
+            else:
+                prediction = predict_probs(words[0], words[1])
+            file.write(prediction + "\n")
+
+    with open("test-A/out.tsv", "w") as file:
+        for _, row in test_data.iterrows():
+            text = prepare_text(str(row[7]))
+            words = word_tokenize(text)
+            if len(words) < 3:
+                prediction = most_common_en_word
+            else:
+                prediction = predict_probs(words[0], words[1])
+            file.write(prediction + "\n")
+
+
+if __name__ == "__main__":
+    # Preapare train data
+    print("Preparing data...")
+    train_data = train_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]
+
+    # declare model
+    print("Preparing model...")
+    model = defaultdict(lambda: defaultdict(lambda: 0))
+
+    # train model
+    print("Model training...")
+    train_trigrams()
+
+    # write outputs
+    print("Writing outputs...")
+    write_output()