final

.ipynb_checkpoints/bayes-checkpoint.ipynb

@@ -0,0 +1,143 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "ce420679-f5aa-4c83-a912-3c4afa982d7e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "D:\\Users\\Adrian\\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": [
+    "import pandas as pd\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "from sklearn.naive_bayes import MultinomialNB\n",
+    "from sklearn.pipeline import make_pipeline\n",
+    "from sklearn.metrics import accuracy_score\n",
+    "\n",
+    "\n",
+    "\n",
+    "df = pd.read_csv(\"train/train.tsv\", sep=\"\\t\", header=None, error_bad_lines=False)\n",
+    "df = df.head(1000)\n",
+    "\n",
+    "\n",
+    "dev_x = pd.read_csv(\"dev-0/in.tsv\", sep=\"\\t\", header=None, error_bad_lines=False)\n",
+    "\n",
+    "\n",
+    "with open('test-A/in.tsv', 'r', encoding='utf8') as file:\n",
+    "    test = file.readlines()\n",
+    "test = pd.Series(test)\n",
+    "\n",
+    "\n",
+    "x = df[1]\n",
+    "y = df[0]\n",
+    "\n",
+    "model = make_pipeline(TfidfVectorizer(), MultinomialNB())\n",
+    "model.fit(x,y)\n",
+    "\n",
+    "pred_dev = model.predict(dev_x[0])\n",
+    "pred_dev = pd.Series(pred_dev)\n",
+    "\n",
+    "with open('dev-0/out.tsv', 'wt') as file:\n",
+    "    for pred in pred_dev:\n",
+    "        file.write(str(pred)+'\\n')\n",
+    "\n",
+    "\n",
+    "pred_test = model.predict(test)\n",
+    "pred_test = pd.Series(pred_test)\n",
+    "pred_test = pred_test.astype('int')\n",
+    "\n",
+    "\n",
+    "        \n",
+    "with open('test-A/out.tsv', 'wt') as file:\n",
+    "    for pred in pred_test:\n",
+    "        file.write(str(pred)+'\\n')\n",
+    "\n",
+    "\n",
+    "\n",
+    "\n",
+    "\n",
+    "        \n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "3e2a9ef0-6da0-4934-8099-378d859ae04e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                                                      0\n",
+      "0     ATP Sztokholm: Juergen Zopp wykorzystał szansę...\n",
+      "1     Krowicki z reprezentacją kobiet aż do igrzysk ...\n",
+      "2     Wielki powrót Łukasza Kubota Odradza się zawsz...\n",
+      "3     Marcel Hirscher wygrał ostatni slalom gigant m...\n",
+      "4     Polki do Czarnogóry z pełnią zaangażowania. Sy...\n",
+      "...                                                 ...\n",
+      "5440  Biało-czerwona siła w Falun. Oni będą reprezen...\n",
+      "5441  Finał WTA Tokio na żywo: Woźniacka - Osaka LIV...\n",
+      "5442  Oni zapisali się w annałach. Hubert Hurkacz 15...\n",
+      "5443  Poprawia się stan Nikiego Laudy. Austriak może...\n",
+      "5444  Liga Mistrzów. Zabójcza końcówka Interu Mediol...\n",
+      "\n",
+      "[5445 rows x 1 columns]\n",
+      "0       ATP Sztokholm: Juergen Zopp wykorzystał szansę...\n",
+      "1       Krowicki z reprezentacją kobiet aż do igrzysk ...\n",
+      "2       Wielki powrót Łukasza Kubota Odradza się zawsz...\n",
+      "3       Marcel Hirscher wygrał ostatni slalom gigant m...\n",
+      "4       Polki do Czarnogóry z pełnią zaangażowania. Sy...\n",
+      "                              ...                        \n",
+      "5442    Biało-czerwona siła w Falun. Oni będą reprezen...\n",
+      "5443    Finał WTA Tokio na żywo: Woźniacka - Osaka LIV...\n",
+      "5444    Oni zapisali się w annałach. Hubert Hurkacz 15...\n",
+      "5445    Poprawia się stan Nikiego Laudy. Austriak może...\n",
+      "5446    Liga Mistrzów. Zabójcza końcówka Interu Mediol...\n",
+      "Length: 5447, dtype: object\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(test)\n",
+    "\n",
+    "\n",
+    "\n",
+    "\n",
+    "print(Xtest)"
+   ]
+  }
+ ],
+ "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
+}

.ipynb_checkpoints/run-checkpoint.py

@@ -0,0 +1,49 @@
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.pipeline import make_pipeline
+from sklearn.metrics import accuracy_score
+
+
+
+df = pd.read_csv("train/train.tsv", sep="\t", header=None, error_bad_lines=False)
+df = df.head(1000)
+
+
+dev_x = pd.read_csv("dev-0/in.tsv", sep="\t", header=None, error_bad_lines=False)
+
+
+with open('test-A/in.tsv', 'r', encoding='utf8') as file:
+    test = file.readlines()
+test = pd.Series(test)
+
+
+x = df[1]
+y = df[0]
+
+model = make_pipeline(TfidfVectorizer(), MultinomialNB())
+model.fit(x,y)
+
+pred_dev = model.predict(dev_x[0])
+pred_dev = pd.Series(pred_dev)
+
+with open('dev-0/out.tsv', 'wt') as file:
+    for pred in pred_dev:
+        file.write(str(pred)+'\n')
+
+
+pred_test = model.predict(test)
+pred_test = pd.Series(pred_test)
+pred_test = pred_test.astype('int')
+
+
+        
+with open('test-A/out.tsv', 'wt') as file:
+    for pred in pred_test:
+        file.write(str(pred)+'\n')
+
+
+
+
+
+        

bayes.ipynb

@@ -0,0 +1,95 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "ce420679-f5aa-4c83-a912-3c4afa982d7e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "D:\\Users\\Adrian\\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": [
+    "import pandas as pd\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "from sklearn.naive_bayes import MultinomialNB\n",
+    "from sklearn.pipeline import make_pipeline\n",
+    "from sklearn.metrics import accuracy_score\n",
+    "\n",
+    "\n",
+    "\n",
+    "df = pd.read_csv(\"train/train.tsv\", sep=\"\\t\", header=None, error_bad_lines=False)\n",
+    "\n",
+    "\n",
+    "\n",
+    "dev_x = pd.read_csv(\"dev-0/in.tsv\", sep=\"\\t\", header=None, error_bad_lines=False)\n",
+    "\n",
+    "\n",
+    "with open('test-A/in.tsv', 'r', encoding='utf8') as file:\n",
+    "    test = file.readlines()\n",
+    "test = pd.Series(test)\n",
+    "\n",
+    "\n",
+    "x = df[1]\n",
+    "y = df[0]\n",
+    "\n",
+    "model = make_pipeline(TfidfVectorizer(), MultinomialNB())\n",
+    "model.fit(x,y)\n",
+    "\n",
+    "pred_dev = model.predict(dev_x[0])\n",
+    "pred_dev = pd.Series(pred_dev)\n",
+    "\n",
+    "with open('dev-0/out.tsv', 'wt') as file:\n",
+    "    for pred in pred_dev:\n",
+    "        file.write(str(pred)+'\\n')\n",
+    "\n",
+    "\n",
+    "pred_test = model.predict(test)\n",
+    "pred_test = pd.Series(pred_test)\n",
+    "pred_test = pred_test.astype('int')\n",
+    "\n",
+    "\n",
+    "        \n",
+    "with open('test-A/out.tsv', 'wt') as file:\n",
+    "    for pred in pred_test:\n",
+    "        file.write(str(pred)+'\\n')\n",
+    "\n",
+    "\n",
+    "\n",
+    "\n",
+    "\n",
+    "        \n"
+   ]
+  }
+ ],
+ "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 +1,49 @@
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.pipeline import make_pipeline
+from sklearn.metrics import accuracy_score
+
+
+
+df = pd.read_csv("train/train.tsv", sep="\t", header=None, error_bad_lines=False)
+df = df.head(1000)
+
+
+dev_x = pd.read_csv("dev-0/in.tsv", sep="\t", header=None, error_bad_lines=False)
+
+
+with open('test-A/in.tsv', 'r', encoding='utf8') as file:
+    test = file.readlines()
+test = pd.Series(test)
+
+
+x = df[1]
+y = df[0]
+
+model = make_pipeline(TfidfVectorizer(), MultinomialNB())
+model.fit(x,y)
+
+pred_dev = model.predict(dev_x[0])
+pred_dev = pd.Series(pred_dev)
+
+with open('dev-0/out.tsv', 'wt') as file:
+    for pred in pred_dev:
+        file.write(str(pred)+'\n')
+
+
+pred_test = model.predict(test)
+pred_test = pd.Series(pred_test)
+pred_test = pred_test.astype('int')
+
+
+        
+with open('test-A/out.tsv', 'wt') as file:
+    for pred in pred_test:
+        file.write(str(pred)+'\n')
+
+
+
+
+
+