s478839

.ipynb_checkpoints/run-checkpoint.ipynb

@@ -0,0 +1,203 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "a8bcddf9-596c-4493-bf2a-8e32255115ce",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import sklearn\n",
+    "from sklearn.naive_bayes import GaussianNB\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "from sklearn.metrics import accuracy_score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "da067d47-0543-48b3-bdf4-844061f827c9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "D:\\Programy\\anaconda3\\lib\\site-packages\\IPython\\core\\interactiveshell.py:3444: FutureWarning: The error_bad_lines argument has been deprecated and will be removed in a future version.\n",
+      "\n",
+      "\n",
+      "  exec(code_obj, self.user_global_ns, self.user_ns)\n",
+      "b'Skipping line 25706: expected 2 fields, saw 3\\nSkipping line 58881: expected 2 fields, saw 3\\nSkipping line 73761: expected 2 fields, saw 3\\n'\n"
+     ]
+    }
+   ],
+   "source": [
+    "train = pd.read_csv('train/train.tsv', header=None, sep='\\t', error_bad_lines=False)\n",
+    "train = train.head(2000)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "94390d90-898c-42df-8482-0e1b8a3ea706",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x_train = train[1]\n",
+    "y_train = train[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "df870ce3-c258-4de0-bbda-f5d71a53163c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x_dev = pd.read_csv('dev-0/in.tsv', header=None, sep='\\t', error_bad_lines=False)\n",
+    "x_dev = x_dev[0]\n",
+    "y_dev = pd.read_csv('dev-0/expected.tsv', header=None, sep='\\t', error_bad_lines=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ce5621d9-655a-46d7-b235-8638daac733e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vectorizer = TfidfVectorizer()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "bca4dc07-fdcd-4ae5-8f24-584a3cda3b79",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x_train = vectorizer.fit_transform(x_train)\n",
+    "x_dev = vectorizer.transform(x_dev)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "96840a5e-bfb9-4fae-a5f9-7acc0d7e4c53",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gnb = GaussianNB()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "aed08803-9aef-43e2-8ee2-1d79458b49ac",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "GaussianNB()"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "gnb.fit(x_train.toarray(), y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "7461bb8d-3b3d-4164-9d47-a62b73dc0e36",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.9418561995597946\n"
+     ]
+    }
+   ],
+   "source": [
+    "dev_predicted =  gnb.predict(x_dev.toarray())\n",
+    "\n",
+    "with open('dev-0/out.tsv', 'wt') as f:\n",
+    "    for i in dev_predicted:\n",
+    "        f.write(str(i)+'\\n')\n",
+    "\n",
+    "dev_out = pd.read_csv('dev-0/out.tsv', header=None, sep='\\t')\n",
+    "dev_expected = pd.read_csv('dev-0/expected.tsv', header=None, sep='\\t')\n",
+    "print(accuracy_score(dev_out, dev_expected))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "2e18bdbe-6d06-42e3-b952-0d5e7bc60325",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open('test-A/in.tsv', 'r', encoding = 'utf-8') as f:\n",
+    "       x_test = f.readlines()\n",
+    "        \n",
+    "x_test = pd.Series(x_test)\n",
+    "x_test = vectorizer.transform(x_test)\n",
+    "\n",
+    "test_predicted = gnb.predict(x_test.toarray())\n",
+    "\n",
+    "with open('test-A/out.tsv', 'wt') as f:\n",
+    "    for i in test_predicted:\n",
+    "        f.write(str(i)+'\\n')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "9463e664-5f74-4a96-8959-03eb224715e7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[NbConvertApp] Converting notebook run.ipynb to script\n",
+      "[NbConvertApp] Writing 1502 bytes to run.py\n"
+     ]
+    }
+   ],
+   "source": [
+    "!jupyter nbconvert --to script run.ipynb"
+   ]
+  }
+ ],
+ "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": "3.9.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

run.ipynb

@@ -0,0 +1,203 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "a8bcddf9-596c-4493-bf2a-8e32255115ce",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import sklearn\n",
+    "from sklearn.naive_bayes import GaussianNB\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "from sklearn.metrics import accuracy_score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "da067d47-0543-48b3-bdf4-844061f827c9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "D:\\Programy\\anaconda3\\lib\\site-packages\\IPython\\core\\interactiveshell.py:3444: FutureWarning: The error_bad_lines argument has been deprecated and will be removed in a future version.\n",
+      "\n",
+      "\n",
+      "  exec(code_obj, self.user_global_ns, self.user_ns)\n",
+      "b'Skipping line 25706: expected 2 fields, saw 3\\nSkipping line 58881: expected 2 fields, saw 3\\nSkipping line 73761: expected 2 fields, saw 3\\n'\n"
+     ]
+    }
+   ],
+   "source": [
+    "train = pd.read_csv('train/train.tsv', header=None, sep='\\t', error_bad_lines=False)\n",
+    "train = train.head(2000)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "94390d90-898c-42df-8482-0e1b8a3ea706",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x_train = train[1]\n",
+    "y_train = train[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "df870ce3-c258-4de0-bbda-f5d71a53163c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x_dev = pd.read_csv('dev-0/in.tsv', header=None, sep='\\t', error_bad_lines=False)\n",
+    "x_dev = x_dev[0]\n",
+    "y_dev = pd.read_csv('dev-0/expected.tsv', header=None, sep='\\t', error_bad_lines=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ce5621d9-655a-46d7-b235-8638daac733e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vectorizer = TfidfVectorizer()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "bca4dc07-fdcd-4ae5-8f24-584a3cda3b79",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x_train = vectorizer.fit_transform(x_train)\n",
+    "x_dev = vectorizer.transform(x_dev)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "96840a5e-bfb9-4fae-a5f9-7acc0d7e4c53",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gnb = GaussianNB()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "aed08803-9aef-43e2-8ee2-1d79458b49ac",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "GaussianNB()"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "gnb.fit(x_train.toarray(), y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "7461bb8d-3b3d-4164-9d47-a62b73dc0e36",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.9418561995597946\n"
+     ]
+    }
+   ],
+   "source": [
+    "dev_predicted =  gnb.predict(x_dev.toarray())\n",
+    "\n",
+    "with open('dev-0/out.tsv', 'wt') as f:\n",
+    "    for i in dev_predicted:\n",
+    "        f.write(str(i)+'\\n')\n",
+    "\n",
+    "dev_out = pd.read_csv('dev-0/out.tsv', header=None, sep='\\t')\n",
+    "dev_expected = pd.read_csv('dev-0/expected.tsv', header=None, sep='\\t')\n",
+    "print(accuracy_score(dev_out, dev_expected))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "2e18bdbe-6d06-42e3-b952-0d5e7bc60325",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open('test-A/in.tsv', 'r', encoding = 'utf-8') as f:\n",
+    "       x_test = f.readlines()\n",
+    "        \n",
+    "x_test = pd.Series(x_test)\n",
+    "x_test = vectorizer.transform(x_test)\n",
+    "\n",
+    "test_predicted = gnb.predict(x_test.toarray())\n",
+    "\n",
+    "with open('test-A/out.tsv', 'wt') as f:\n",
+    "    for i in test_predicted:\n",
+    "        f.write(str(i)+'\\n')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "9463e664-5f74-4a96-8959-03eb224715e7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[NbConvertApp] Converting notebook run.ipynb to script\n",
+      "[NbConvertApp] Writing 1502 bytes to run.py\n"
+     ]
+    }
+   ],
+   "source": [
+    "!jupyter nbconvert --to script run.ipynb"
+   ]
+  }
+ ],
+ "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": "3.9.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

run.py

@@ -0,0 +1,90 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[1]:
+
+
+import numpy as np
+import pandas as pd
+import sklearn
+from sklearn.naive_bayes import GaussianNB
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics import accuracy_score
+
+
+# In[2]:
+
+
+train = pd.read_csv('train/train.tsv', header=None, sep='\t', error_bad_lines=False)
+train = train.head(2000)
+
+
+# In[3]:
+
+
+x_train = train[1]
+y_train = train[0]
+
+
+# In[4]:
+
+
+x_dev = pd.read_csv('dev-0/in.tsv', header=None, sep='\t', error_bad_lines=False)
+x_dev = x_dev[0]
+y_dev = pd.read_csv('dev-0/expected.tsv', header=None, sep='\t', error_bad_lines=False)
+
+
+# In[5]:
+
+
+vectorizer = TfidfVectorizer()
+
+
+# In[6]:
+
+
+x_train = vectorizer.fit_transform(x_train)
+x_dev = vectorizer.transform(x_dev)
+
+
+# In[7]:
+
+
+gnb = GaussianNB()
+
+
+# In[8]:
+
+
+gnb.fit(x_train.toarray(), y_train)
+
+
+# In[9]:
+
+
+dev_predicted =  gnb.predict(x_dev.toarray())
+
+with open('dev-0/out.tsv', 'wt') as f:
+    for i in dev_predicted:
+        f.write(str(i)+'\n')
+
+dev_out = pd.read_csv('dev-0/out.tsv', header=None, sep='\t')
+dev_expected = pd.read_csv('dev-0/expected.tsv', header=None, sep='\t')
+print(accuracy_score(dev_out, dev_expected))
+
+
+# In[10]:
+
+
+with open('test-A/in.tsv', 'r', encoding = 'utf-8') as f:
+       x_test = f.readlines()
+        
+x_test = pd.Series(x_test)
+x_test = vectorizer.transform(x_test)
+
+test_predicted = gnb.predict(x_test.toarray())
+
+with open('test-A/out.tsv', 'wt') as f:
+    for i in test_predicted:
+        f.write(str(i)+'\n')
+