s443930

main.py

@@ -0,0 +1,80 @@
+import lzma
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.naive_bayes import BernoulliNB
+import numpy as np
+import csv
+
+
+X = []
+with lzma.open('train/in.tsv.xz') as f:
+    for line in f:
+        X.append(line.decode('utf-8'))
+
+Y = []
+with open('train/expected.tsv') as f:
+    for line in f:
+        Y.append(line.replace('\n', ''))
+
+
+vectorizer = TfidfVectorizer()
+textVectors = vectorizer.fit_transform(X)
+
+trainY = np.array(Y)
+
+bernoulli = BernoulliNB()
+bernoulli.fit(textVectors, trainY)
+
+# dev-0
+testX = []
+with open('dev-0/in.tsv', encoding='utf8') as f:
+    for line in f:
+        testX.append(line)
+
+testX = vectorizer.transform(testX)
+predictedY = bernoulli.predict(testX)
+
+expectedY = []
+with open('dev-0/expected.tsv') as f:
+    for line in f:
+        expectedY.append(line.replace('\n', ''))
+
+with open('dev-0/out.tsv', 'w', newline='') as f:
+    writer = csv.writer(f)
+    writer.writerows(predictedY)
+
+
+# dev-1
+testX = []
+
+with open('dev-1/in.tsv', encoding='utf8') as f:
+    for line in f:
+        testX.append(line)
+
+testX = vectorizer.transform(testX)
+predictedY = bernoulli.predict(testX)
+
+expectedY = []
+
+with open('dev-1/expected.tsv') as f:
+    for line in f:
+        expectedY.append(line.replace('\n', ''))
+
+with open('dev-1/out.tsv', 'w', newline='') as f:
+    writer = csv.writer(f)
+    writer.writerows(predictedY)
+
+
+# test-A
+testX = []
+
+with open('test-A/in.tsv', encoding='utf8') as f:
+    for line in f:
+        testX.append(line)
+
+testX = vectorizer.transform(testX)
+
+predictedY = bernoulli.predict(testX)
+
+with open('test-A/out.tsv', 'w', newline='') as f:
+    writer = csv.writer(f)
+    writer.writerows(predictedY)

sheSaid.ipynb

@@ -0,0 +1,277 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 96,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import lzma"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 97,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = []\n",
+    "\n",
+    "with lzma.open('train/in.tsv.xz') as f:\n",
+    "    for line in f:\n",
+    "        X.append(line.decode('utf-8'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 98,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Y = []\n",
+    "\n",
+    "with open('train/expected.tsv') as f:\n",
+    "    for line in f:\n",
+    "        txt = line\n",
+    "        txt = txt.replace('\\n', '')\n",
+    "        Y.append(txt)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 99,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "\n",
+    "vectorizer = TfidfVectorizer()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 100,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "textVectors = vectorizer.fit_transform(X)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 101,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "matrix([[0., 0., 0., ..., 0., 0., 0.]])"
+      ]
+     },
+     "execution_count": 101,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "textVectors[0].todense()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 102,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.naive_bayes import BernoulliNB\n",
+    "import numpy as np\n",
+    "\n",
+    "trainY = np.array(Y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 103,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "BernoulliNB()"
+      ]
+     },
+     "execution_count": 103,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "bernoulli = BernoulliNB()\n",
+    "bernoulli.fit(textVectors, trainY)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 104,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import csv\n",
+    "\n",
+    "testX = []\n",
+    "\n",
+    "with open('dev-0/in.tsv', encoding='utf8') as f:\n",
+    "    for line in f:\n",
+    "        testX.append(line)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 105,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "testX = vectorizer.transform(testX)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 106,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "predictedY = bernoulli.predict(testX)\n",
+    "\n",
+    "with open('dev-0/out.tsv', 'w', newline='') as f:\n",
+    "    writer = csv.writer(f)\n",
+    "    writer.writerows(predictedY)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 107,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "expectedY = []\n",
+    "with open('dev-0/expected.tsv') as f:\n",
+    "    for line in f:\n",
+    "        txt = line\n",
+    "        txt = txt.replace('\\n', '')\n",
+    "        expectedY.append(txt)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 108,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.6577260876531162"
+      ]
+     },
+     "execution_count": 108,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "bernoulli.score(testX, expectedY)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 109,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Score for dev-1: 0.6406778795193032\n"
+     ]
+    }
+   ],
+   "source": [
+    "# dev-1\n",
+    "testX = []\n",
+    "\n",
+    "with open('dev-1/in.tsv', encoding='utf8') as f:\n",
+    "    for line in f:\n",
+    "        testX.append(line)\n",
+    "\n",
+    "testX = vectorizer.transform(testX)\n",
+    "\n",
+    "predictedY = bernoulli.predict(testX)\n",
+    "\n",
+    "expectedY = []\n",
+    "\n",
+    "with open('dev-1/expected.tsv') as f:\n",
+    "    for line in f:\n",
+    "        expectedY.append(line.replace('\\n', ''))\n",
+    "\n",
+    "print('Score for dev-1:', bernoulli.score(testX, expectedY))\n",
+    "\n",
+    "with open('dev-1/out.tsv', 'w', newline='') as f:\n",
+    "    writer = csv.writer(f)\n",
+    "    writer.writerows(predictedY)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 110,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# test-A\n",
+    "testX = []\n",
+    "\n",
+    "with open('test-A/in.tsv', encoding='utf8') as f:\n",
+    "    for line in f:\n",
+    "        testX.append(line)\n",
+    "\n",
+    "testX = vectorizer.transform(testX)\n",
+    "\n",
+    "predictedY = bernoulli.predict(testX)\n",
+    "\n",
+    "with open('test-A/out.tsv', 'w', newline='') as f:\n",
+    "    writer = csv.writer(f)\n",
+    "    writer.writerows(predictedY)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "interpreter": {
+   "hash": "3a5b3979b9a2fc2c8e649de363a592bbf5a2c9da164843b1adb5b45661722ad0"
+  },
+  "kernelspec": {
+   "display_name": "Python 3.8.10 64-bit",
+   "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": "3.8.10"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}