440054

.gitignore

@@ -6,3 +6,5 @@
 *.o
 .DS_Store
 .token
+.vscode/*
+.ipynb_c*

run.py

@@ -0,0 +1,106 @@
+import pandas as pd
+import csv
+import regex as re
+import nltk
+from collections import Counter, defaultdict
+import string
+import unicodedata
+
+def main():
+    try:
+        nltk.data.find('tokenizers/punkt')
+    except LookupError:
+        nltk.download('punkt')
+
+    with open("in-header.tsv") as f:
+        in_cols = f.read().strip().split("\t")
+    
+    with open("out-header.tsv") as f:
+        out_cols = f.read().strip().split("\t")
+
+    data = pd.read_csv(
+        "train/in.tsv.xz",
+        sep="\t",
+        on_bad_lines='skip',
+        header=None,
+        # names=in_cols,
+        quoting=csv.QUOTE_NONE,
+    )
+
+    train_labels = pd.read_csv(
+        "train/expected.tsv",
+        sep="\t",
+        on_bad_lines='skip',
+        header=None,
+        # names=out_cols,
+        quoting=csv.QUOTE_NONE,
+    )
+
+    train_data = data[[7, 6]]
+    train_data = pd.concat([train_data, train_labels], axis=1)
+
+    train_data["final"] = train_data[7] + train_data[0] + train_data[6]
+
+    model = defaultdict(lambda: defaultdict(lambda: 0))
+
+    train_model(train_data, model)
+    predict_data("dev-0/in.tsv.xz", "dev-0/out.tsv", model)
+    predict_data("test-A/in.tsv.xz", "test-A/out.tsv", model)
+
+def clean_text(text): 
+    return re.sub(r"\p{P}", "", str(text).lower().replace("-\\n", "").replace("\\n", " "))
+
+def train_model(data, model):
+    for _, row in data.iterrows():
+        words = nltk.word_tokenize(clean_text(row["final"]))
+        for w1, w2 in nltk.bigrams(words, pad_left=True, pad_right=True):
+            if w1 and w2:
+                model[w2][w1] += 1
+    for w1 in model:
+        total_count = float(sum(model[w1].values()))
+        for w2 in model[w1]:
+            model[w2][w1] /= total_count
+
+
+def predict(word, model):
+    predictions = dict(model[word])
+    most_common = dict(Counter(predictions).most_common(5))
+
+    total_prob = 0.0
+    str_prediction = ""
+
+    for word, prob in most_common.items():
+        total_prob += prob
+        str_prediction += f"{word}:{prob} "
+
+    if not total_prob:
+        return "the:0.2 be:0.2 to:0.2 of:0.1 and:0.1 a:0.1 :0.1"
+
+    if 1 - total_prob >= 0.01:
+        str_prediction += f":{1-total_prob}"
+    else:
+        str_prediction += f":0.01"
+
+    return str_prediction
+
+
+def predict_data(read_path, save_path, model):
+    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 = nltk.word_tokenize(clean_text(row[6]))
+            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], model)
+            file.write(prediction + "\n")
+
+
+if __name__ == "__main__":
+    main()

testing.ipynb

@@ -0,0 +1,211 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "21c9b695",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import csv\n",
+    "import regex as re\n",
+    "import nltk\n",
+    "from collections import Counter, defaultdict\n",
+    "import string\n",
+    "import unicodedata\n",
+    "\n",
+    "def clean_text(text): \n",
+    "    return re.sub(r\"\\p{P}\", \"\", str(text).lower().replace(\"-\\\\n\", \"\").replace(\"\\\\n\", \" \"))\n",
+    "\n",
+    "def train_model(data, model):\n",
+    "    for _, row in data.iterrows():\n",
+    "        words = nltk.word_tokenize(clean_text(row[\"final\"]))\n",
+    "        for w1, w2 in nltk.bigrams(words, pad_left=True, pad_right=True):\n",
+    "            if w1 and w2:\n",
+    "                model[w2][w1] += 1\n",
+    "    for w1 in model:\n",
+    "        total_count = float(sum(model[w1].values()))\n",
+    "        for w2 in model[w1]:\n",
+    "            model[w2][w1] /= total_count\n",
+    "\n",
+    "\n",
+    "def predict(word, model):\n",
+    "    predictions = dict(model[word])\n",
+    "    most_common = dict(Counter(predictions).most_common(5))\n",
+    "\n",
+    "    total_prob = 0.0\n",
+    "    str_prediction = \"\"\n",
+    "\n",
+    "    for word, prob in most_common.items():\n",
+    "        total_prob += prob\n",
+    "        str_prediction += f\"{word}:{prob} \"\n",
+    "\n",
+    "    if not total_prob:\n",
+    "        return \"the:0.2 be:0.2 to:0.2 of:0.1 and:0.1 a:0.1 :0.1\"\n",
+    "\n",
+    "    if 1 - total_prob >= 0.01:\n",
+    "        str_prediction += f\":{1-total_prob}\"\n",
+    "    else:\n",
+    "        str_prediction += f\":0.01\"\n",
+    "\n",
+    "    return str_prediction\n",
+    "\n",
+    "\n",
+    "def predict_data(read_path, save_path, model):\n",
+    "    data = pd.read_csv(\n",
+    "        read_path, sep=\"\\t\", error_bad_lines=False, header=None, quoting=csv.QUOTE_NONE\n",
+    "    )\n",
+    "    with open(save_path, \"w\") as file:\n",
+    "        for _, row in data.iterrows():\n",
+    "            words = nltk.word_tokenize(clean_text(row[7]))\n",
+    "            if len(words) < 3:\n",
+    "                prediction = \"the:0.2 be:0.2 to:0.2 of:0.1 and:0.1 a:0.1 :0.1\"\n",
+    "            else:\n",
+    "                prediction = predict(words[-1], model)\n",
+    "            file.write(prediction + \"\\n\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "e39473e2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"in-header.tsv\") as f:\n",
+    "    in_cols = f.read().strip().split(\"\\t\")\n",
+    "\n",
+    "with open(\"out-header.tsv\") as f:\n",
+    "    out_cols = f.read().strip().split(\"\\t\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "bde510c9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['FileId', 'Year', 'LeftContext', 'RightContext']"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "in_cols"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "0e8b31dd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Word']"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "out_cols"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7662d802",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = pd.read_csv(\n",
+    "    \"train/in.tsv.xz\",\n",
+    "    sep=\"\\t\",\n",
+    "    on_bad_lines='skip',\n",
+    "    header=None,\n",
+    "    # names=in_cols,\n",
+    "    quoting=csv.QUOTE_NONE,\n",
+    ")\n",
+    "\n",
+    "train_labels = pd.read_csv(\n",
+    "    \"train/expected.tsv\",\n",
+    "    sep=\"\\t\",\n",
+    "    on_bad_lines='skip',\n",
+    "    header=None,\n",
+    "    # names=out_cols,\n",
+    "    quoting=csv.QUOTE_NONE,\n",
+    ")\n",
+    "\n",
+    "train_data = data[[7, 6]]\n",
+    "train_data = pd.concat([train_data, train_labels], axis=1)\n",
+    "\n",
+    "train_data[\"final\"] = train_data[7] + train_data[0] + train_data[6]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c3d2cfec",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bd92ba07",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "model = defaultdict(lambda: defaultdict(lambda: 0))\n",
+    "\n",
+    "train_model(train_data, model)\n",
+    "predict_data(\"dev-0/in.tsv.xz\", \"dev-0/out.tsv\", model)\n",
+    "predict_data(\"test-A/in.tsv.xz\", \"test-A/out.tsv\", model)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ad23240e",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}