Bayes 2

.ipynb_checkpoints/Bayes-checkpoint.ipynb

@@ -0,0 +1,110 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "from sklearn.naive_bayes import MultinomialNB\n",
+    "from sklearn.pipeline import make_pipeline\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"train/in.tsv\") as f:\n",
+    "    x_train = f.readlines()\n",
+    "\n",
+    "with open(\"train/expected.tsv\") as f:\n",
+    "    y_train = f.readlines()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([1, 0, 0, ..., 0, 0, 1])"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "y_train = LabelEncoder().fit_transform(y_train)\n",
+    "y_train"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pipeline = make_pipeline(TfidfVectorizer(),MultinomialNB())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = pipeline.fit(x_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"dev-0/in.tsv\") as f:\n",
+    "    x_dev = f.readlines()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prediction = model.predict(x_dev)\n",
+    "np.savetxt(\"dev-0/out.tsv\", prediction, fmt='%d')"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

Bayes.ipynb

@@ -0,0 +1,130 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "from sklearn.naive_bayes import MultinomialNB\n",
+    "from sklearn.pipeline import make_pipeline\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"train/in.tsv\") as f:\n",
+    "    x_train = f.readlines()\n",
+    "\n",
+    "with open(\"train/expected.tsv\") as f:\n",
+    "    y_train = f.readlines()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([1, 0, 0, ..., 0, 0, 1])"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "y_train = LabelEncoder().fit_transform(y_train)\n",
+    "y_train"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pipeline = make_pipeline(TfidfVectorizer(),MultinomialNB())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = pipeline.fit(x_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"dev-0/in.tsv\") as f:\n",
+    "    x_dev = f.readlines()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prediction = model.predict(x_dev)\n",
+    "np.savetxt(\"dev-0/out.tsv\", prediction, fmt='%d')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"test-A/in.tsv\") as f:\n",
+    "    x_test = f.readlines()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prediction = model.predict(x_test)\n",
+    "np.savetxt(\"test-A/out.tsv\", prediction, fmt='%d')"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

program.py

@@ -0,0 +1,29 @@
+import numpy as np
+from sklearn.preprocessing import LabelEncoder
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.pipeline import make_pipeline
+from sklearn.feature_extraction.text import TfidfVectorizer
+
+with open("train/in.tsv") as f:
+    x_train = f.readlines()
+
+with open("train/expected.tsv") as f:
+    y_train = f.readlines()
+
+y_train = LabelEncoder().fit_transform(y_train)
+
+pipeline = make_pipeline(TfidfVectorizer(),MultinomialNB())
+
+model = pipeline.fit(x_train, y_train)
+
+with open("dev-0/in.tsv") as f:
+    x_dev = f.readlines()
+
+prediction = model.predict(x_dev)
+np.savetxt("dev-0/out.tsv", prediction, fmt='%d')
+
+with open("test-A/in.tsv") as f:
+    x_test = f.readlines()
+
+prediction = model.predict(x_test)
+np.savetxt("test-A/out.tsv", prediction, fmt='%d')

wyniki.txt

@@ -0,0 +1,6 @@
+Likelihood	0.0000
+Accuracy	0.7367
+F1.0	0.4367
+Precision	0.8997
+Recall	0.2883
+