result

run.ipynb

@@ -0,0 +1,281 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 100,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import lzma\n",
+    "import sys\n",
+    "from io import StringIO\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "import pandas as pd\n",
+    "import numpy\n",
+    "\n",
+    "pathX = \"./train/in.tsv.xz\"\n",
+    "# pathX = \"./train/in.tsv\"\n",
+    "pathY = \"./train/expected.tsv\"\n",
+    "nrows = 10000"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 101,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# data = lzma.open(pathX, mode='rt', encoding='utf-8').read()\n",
+    "# stringIO = StringIO(data)\n",
+    "# df = pd.read_csv(stringIO, sep=\"\\t\", header=None)\n",
+    "df = pd.read_csv(pathX, sep='\\t', nrows=nrows, header=None)\n",
+    "df = df.drop(df.columns[1], axis=1)\n",
+    "topics = pd.read_csv(pathY, sep='\\t', nrows=nrows, header=None)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 102,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "10000\n",
+      "10000\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(len(df.index))\n",
+    "\n",
+    "print(len(topics.index))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 103,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>0</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>8910</th>\n",
+       "      <td>What? It isn't a fake memo. It's a real memo. ...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                                      0\n",
+       "8910  What? It isn't a fake memo. It's a real memo. ..."
+      ]
+     },
+     "execution_count": 103,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.sample()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 104,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['00', '000', '00000001', ..., 'αsynuclein', 'ಠ_ಠ', 'fibrosis'],\n",
+       "      dtype=object)"
+      ]
+     },
+     "execution_count": 104,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "vectorizer = TfidfVectorizer(lowercase=True, stop_words=['english'])\n",
+    "X = vectorizer.fit_transform(df.to_numpy().ravel())\n",
+    "vectorizer.get_feature_names_out()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 105,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# vectorizer.transform(\"Ala ma kotka\".lower().split())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 106,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = df.reset_index()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 107,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tfidfVector = vectorizer.transform(df[0])\n",
+    "\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 108,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Python310\\lib\\site-packages\\sklearn\\utils\\validation.py:993: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
+      "  y = column_or_1d(y, warn=True)\n",
+      "c:\\Python310\\lib\\site-packages\\sklearn\\utils\\validation.py:593: FutureWarning: np.matrix usage is deprecated in 1.0 and will raise a TypeError in 1.2. Please convert to a numpy array with np.asarray. For more information see: https://numpy.org/doc/stable/reference/generated/numpy.matrix.html\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "GaussianNB()"
+      ]
+     },
+     "execution_count": 108,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.naive_bayes import GaussianNB\n",
+    "\n",
+    "gnb = GaussianNB()\n",
+    "gnb.fit(tfidfVector.todense(), topics)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 109,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "testXPath = \"./dev-0/in.tsv.xz\"\n",
+    "testYPath = \"./dev-0/expected.tsv\"\n",
+    "\n",
+    "testX = pd.read_csv(testXPath, sep='\\t', nrows=nrows, header=None)\n",
+    "\n",
+    "testY = pd.read_csv(testYPath, sep='\\t', nrows=nrows, header=None)\n",
+    "testXtfidfVector = vectorizer.transform(testX[0])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 115,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "testXPath = \"./test-A/in.tsv.xz\"\n",
+    "testYPath = \"./test-A/expected.tsv\"\n",
+    "\n",
+    "testX = pd.read_csv(testXPath, sep='\\t', nrows=nrows, header=None)\n",
+    "\n",
+    "# testY = pd.read_csv(testYPath, sep='\\t', nrows=nrows, header=None)\n",
+    "testXtfidfVector = vectorizer.transform(testX[0])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 118,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Python310\\lib\\site-packages\\sklearn\\utils\\validation.py:593: FutureWarning: np.matrix usage is deprecated in 1.0 and will raise a TypeError in 1.2. Please convert to a numpy array with np.asarray. For more information see: https://numpy.org/doc/stable/reference/generated/numpy.matrix.html\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[0 1 0 ... 0 0 1]\n"
+     ]
+    }
+   ],
+   "source": [
+    "pred = gnb.predict(testXtfidfVector.todense())\n",
+    "print(pred)\n",
+    "\n",
+    "import csv\n",
+    "with open(testYPath, 'w', newline='') as f_output:\n",
+    "    tsv_output = csv.writer(f_output, delimiter='\\n')\n",
+    "    tsv_output.writerow(pred)"
+   ]
+  }
+ ],
+ "metadata": {
+  "interpreter": {
+   "hash": "369f2c481f4da34e4445cda3fffd2e751bd1c4d706f27375911949ba6bb62e1c"
+  },
+  "kernelspec": {
+   "display_name": "Python 3.10.4 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": "3.10.4"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

run.py

@@ -0,0 +1,22 @@
+import lzma
+import sys
+from io import StringIO
+from sklearn.feature_extraction.text import TfidfVectorizer
+
+
+import pandas as pd
+
+
+
+pathX = "./train/in.tsv.xz"
+pathY = "./train/expected.tsv"
+    
+data = lzma.open(pathX, mode='rt', encoding='utf-8').read()
+stringIO = StringIO(data)
+df = pd.read_csv(stringIO, sep="\t", header=None)
+df = df.drop(df.columns[[1]], axis=1)
+topics = pd.read_csv(pathY, sep='\t', header=None)
+
+vectorizer = TfidfVectorizer()
+X = vectorizer.fit_transform(df.to_numpy().ravel())
+print(vectorizer.get_feature_names_out())