Test 2 Outputs

LogReg_Test.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 38,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -11,21 +11,22 @@
     "import torch\n",
     "import csv\n",
     "from nltk.tokenize import word_tokenize\n",
-    "from gensim.models import Word2Vec\n",
-    "import gensim.downloader"
+    "#from gensim.models import Word2Vec\n",
+    "import gensim.downloader as api"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 39,
    "metadata": {},
    "outputs": [],
    "source": [
+    "#Sieć neuronowa z ćwiczeń 8\n",
     "class NeuralNetwork(torch.nn.Module): \n",
-    "    def __init__(self, input_size, hidden_size, num_classes):\n",
+    "    def __init__(self, hidden_size):\n",
     "        super(NeuralNetwork, self).__init__()\n",
-    "        self.l1 = torch.nn.Linear(input_size, hidden_size)\n",
-    "        self.l2 = torch.nn.Linear(hidden_size, num_classes)\n",
+    "        self.l1 = torch.nn.Linear(300, hidden_size) #Korzystamy z Googlowego word2vec-google-news-300 który ma zawsze na wejściu wymiar 300\n",
+    "        self.l2 = torch.nn.Linear(hidden_size, 1)\n",
     "\n",
     "    def forward(self, x):\n",
     "        x = self.l1(x)\n",
@@ -37,68 +38,35 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 40,
    "metadata": {},
    "outputs": [],
    "source": [
-    "col_names = ['content', 'id', 'label']\n"
+    "# Wczytanie X i Y do Train oraz X do Dev i Test\n",
+    "X_train = pd.read_table('train/in.tsv', sep='\\t', error_bad_lines=False, quoting=3, header=None, names=['content', 'id'], usecols=['content'])\n",
+    "y_train = pd.read_table('train/expected.tsv', sep='\\t', error_bad_lines=False, quoting=3, header=None, names=['label'])\n",
+    "X_dev = pd.read_table('dev-0/in.tsv', sep='\\t', error_bad_lines=False, header=None, quoting=3, names=['content', 'id'], usecols=['content'])\n",
+    "X_test = pd.read_table('test-A/in.tsv', sep='\\t', error_bad_lines=False, header=None, quoting=3, names=['content', 'id'], usecols=['content'])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 41,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Wczytanie danych...\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "print('Wczytanie danych...')\n",
-    "# loading dataset\n",
-    "train_set_features = pd.read_table('train/in.tsv.xz', error_bad_lines=False, quoting=csv.QUOTE_NONE, header=None, names=col_names[:2])\n",
-    "train_set_labels = pd.read_table('train/expected.tsv', error_bad_lines=False, quoting=csv.QUOTE_NONE, header=None, names=col_names[2:])\n",
-    "dev_set = pd.read_table('dev-0/in.tsv.xz', error_bad_lines=False, header=None, quoting=csv.QUOTE_NONE, names=col_names[:2])\n",
-    "test_set = pd.read_table('test-A/in.tsv.xz', error_bad_lines=False, header=None, quoting=csv.QUOTE_NONE, names=col_names[:2])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Preprocessing danych...\n"
-     ]
-    }
-   ],
-   "source": [
-    "print('Preprocessing danych...')\n",
+    "# Preprocessing danych\n",
     "# lowercase\n",
-    "X_train = train_set_features['content'].str.lower()\n",
-    "y_train = train_set_labels['label']"
+    "# https://www.datacamp.com/community/tutorials/case-conversion-python\n",
+    "X_train = X_train.content.str.lower()\n",
+    "y_train = y_train['label']\n",
+    "X_dev = X_dev.content.str.lower()\n",
+    "X_test = X_test.content.str.lower()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "X_dev = dev_set['content'].str.lower()\n",
-    "X_test = test_set['content'].str.lower()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 42,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -110,55 +78,40 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[==================================================] 100.0% 1662.8/1662.8MB downloaded\n"
-     ]
-    }
-   ],
-   "source": [
-    "# word2vec\n",
-    "word2vec = gensim.downloader.load('word2vec-google-news-300')\n",
-    "X_train = [np.mean([word2vec[word] for word in content if word in word2vec] or [np.zeros(300)], axis=0) for content in X_train]\n",
-    "X_dev = [np.mean([word2vec[word] for word in content if word in word2vec] or [np.zeros(300)], axis=0) for content in X_dev]\n",
-    "X_test = [np.mean([word2vec[word] for word in content if word in word2vec] or [np.zeros(300)], axis=0) for content in X_test]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 44,
    "metadata": {},
    "outputs": [],
    "source": [
-    "model = NeuralNetwork(300, 600, 1)\n",
-    "\n",
-    "criterion = torch.nn.BCELoss()\n",
-    "optimizer = torch.optim.SGD(model.parameters(), lr = 0.01)\n",
-    "\n",
-    "batch_size = 10"
+    "# word2vec\n",
+    "# https://radimrehurek.com/gensim/auto_examples/howtos/run_downloader_api.html\n",
+    "w2v = api.load('word2vec-google-news-300')\n",
+    "X_train = [np.mean([w2v[w] for w in content if w in w2v] or [np.zeros(300)], axis=0) for content in X_train]\n",
+    "X_dev = [np.mean([w2v[w] for w in content if w in w2v] or [np.zeros(300)], axis=0) for content in X_dev]\n",
+    "X_test = [np.mean([w2v[w] for w in content if w in w2v] or [np.zeros(300)], axis=0) for content in X_test]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 45,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Trenowanie modelu...\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "print('Trenowanie modelu...')\n",
-    "for epoch in range(6):\n",
+    "model = NeuralNetwork(600)\n",
+    "\n",
+    "criterion = torch.nn.BCELoss()\n",
+    "optimizer = torch.optim.SGD(model.parameters(), lr = 0.1)\n",
+    "\n",
+    "batch_size = 15"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Trening modelu z ćwiczeń 8\n",
+    "for epoch in range(5):\n",
     "    model.train()\n",
     "    for i in range(0, y_train.shape[0], batch_size):\n",
     "        X = X_train[i:i+batch_size]\n",
@@ -176,7 +129,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 47,
    "metadata": {},
    "outputs": [
     {
@@ -218,13 +171,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 49,
    "metadata": {},
    "outputs": [],
    "source": [
     "dev_prediction.tofile('./dev-0/out.tsv', sep='\\n')\n",
     "test_prediction.tofile('./test-A/out.tsv', sep='\\n')"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {