update

sentiment.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -26,16 +26,6 @@
     "    return processed_text.translate(str.maketrans('','', string.punctuation))"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import nltk\n",
-    "nltk.download()"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -97,171 +87,13 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "\n",
-    "sentence = input(\"Enter the sentence: \")\n",
-    "\n",
-    "preprocess_text(sentence)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "\n",
-    "df_train = pd.read_csv('recensioni_train.csv')\n",
-    "df_test = pd.read_csv('recensioni_test.csv')\n",
-    "\n",
-    "X_train = df_train['text'].apply(preprocess_text)\n",
-    "X_test = df_test['text'].apply(preprocess_text)\n",
-    "\n",
-    "tags_train = df_train['tag']\n",
-    "tags_test = df_test['tag']\n",
-    "\n",
-    "y_train = []\n",
-    "y_test = []\n",
-    "\n",
-    "#Train\n",
-    "for e in tags_train:\n",
-    "    if e=='pos':\n",
-    "        y_train.append(1)\n",
-    "    else:\n",
-    "        y_train.append(0)\n",
-    "\n",
-    "#Test\n",
-    "for e in tags_test:\n",
-    "    if e=='pos':\n",
-    "        y_test.append(1)\n",
-    "    else:\n",
-    "        y_test.append(0)\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#######################\n",
-    "\n",
-    "tokenizer_train = Tokenizer(num_words=10000)\n",
-    "tokenizer_train.fit_on_texts(X_train)\n",
-    "sequences_train = tokenizer_train.texts_to_sequences(X_train)\n",
-    "word_index_train = tokenizer_train.word_index\n",
-    "print('Found %s unique tokens' % len(word_index_train))\n",
-    "\n",
     "print(X_train[0])\n",
     "print(y_train[0])\n",
     "\n",
-    "#######################\n",
-    "\n",
-    "tokenizer_test = Tokenizer(num_words=10000)\n",
-    "tokenizer_test.fit_on_texts(X_test)\n",
-    "sequences_test = tokenizer_test.texts_to_sequences(X_test)\n",
-    "word_index_test = tokenizer_test.word_index\n",
-    "print('Found %s unique tokens' % len(word_index_test))\n",
-    "\n",
     "print(X_test[0])\n",
     "print(y_test[0])"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#Dataset NGT\n",
-    "\n",
-    "tokenizer_ngt = Tokenizer(num_words=10000)\n",
-    "tokenizer_ngt.fit_on_texts(X_ngt)\n",
-    "sequences_ngt = tokenizer_ngt.texts_to_sequences(X_ngt)\n",
-    "word_index_ngt = tokenizer_ngt.word_index\n",
-    "print('Found %s unique tokens' % len(word_index_ngt))\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#Dataset NGT\n",
-    "\n",
-    "X_ngt = pad_sequences(sequences_ngt)\n",
-    "y_ngt = np.asarray(y_ngt)\n",
-    "indices_ngt = np.arange(X_ngt.shape[0])\n",
-    "\n",
-    "\n",
-    "np.random.shuffle(indices_ngt)\n",
-    "X_ngt = X_ngt[indices_ngt]\n",
-    "y_ngt = y_ngt[indices_ngt]\n",
-    "\n",
-    "X_train, X_test, y_train, y_test = train_test_split(X_ngt, y_ngt, test_size=0.2)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(X_train[0])\n",
-    "print(y_train[0])\n",
-    "\n",
-    "print(X_test[0])\n",
-    "print(y_test[0])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "X_train = pad_sequences(sequences_train)\n",
-    "y_train = np.asarray(y_train)\n",
-    "indices_train = np.arange(X_train.shape[0])\n",
-    "\n",
-    "\n",
-    "X_test = pad_sequences(sequences_test)\n",
-    "y_test = np.asarray(y_test)\n",
-    "indices_test = np.arange(X_test.shape[0])\n",
-    "\n",
-    "print(indices_train)\n",
-    "print(X_train[0])\n",
-    "print(y_train[0])\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "np.random.shuffle(indices_train)\n",
-    "X_train = X_train[indices_train]\n",
-    "y_train = y_train[indices_train]\n",
-    "\n",
-    "\n",
-    "np.random.shuffle(indices_test)\n",
-    "X_test = X_train[indices_test]\n",
-    "y_test = y_train[indices_test]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "X_train.shape\n",
-    "\n",
-    "print(X_train.dtype)\n"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -277,8 +109,6 @@
     "model.add(Dense(32, activation='relu'))\n",
     "model.add(Dense(1, activation='sigmoid'))\n",
     "\n",
-    "#model.compile(optimizer='SGD', loss='binary_crossentropy', metrics=['acc'])\n",
-    "#model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['acc'])\n",
     "model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['acc'])\n",
     "\n",
     "history = model.fit(X_train, y_train, epochs=10, batch_size=32, validation_data=(X_test, y_test))"
@@ -331,9 +161,7 @@
    "source": [
     "\n",
     "#Salvataggio del modello\n",
-    "\n",
-    "model.save('binary.keras')\n",
-    "\n"
+    "model.save('model.keras')"
    ]
   },
   {
@@ -341,62 +169,15 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# Dataset ngt\n",
-    "# model.add(Dense(512, activation='relu'))\n",
-    "# model.add(Dense(8, activation='relu'))\n",
-    "# model.add(Dense(1, activation='sigmoid'))\n",
-    "\n",
-    "\n",
-    "# model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['acc'])\n",
-    "\n",
-    "# history = model.fit(X_train, y_train, epochs=10, batch_size=32, validation_data=(X_test, y_test))\n",
-    "\n",
-    "\n",
-    "# Epoch 10/10\n",
-    "# 100/100 [==============================] - 0s 3ms/step - loss: 0.6099 - acc: 0.6712 - val_loss: 0.6311 - val_acc: 0.6525\n",
-    "\n",
-    "\n",
-    "################################################\n",
-    "\n",
-    "\n",
-    "# Altro dataset\n",
-    "# model.add(Dense(512, activation='relu'))\n",
-    "# model.add(Dense(32, activation='relu'))\n",
-    "# model.add(Dense(1, activation='sigmoid'))\n",
-    "\n",
-    "# model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['acc'])\n",
-    "\n",
-    "# history = model.fit(X_train, y_train, epochs=5, batch_size=32, validation_data=(X_test, y_test))\n",
-    "\n",
-    "# Epoch 5/5\n",
-    "# 63/63 [==============================] - 0s 3ms/step - loss: 0.5344 - acc: 0.7185 - val_loss: 0.5255 - val_acc: 0.7525"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "1/1 [==============================] - 0s 51ms/step\n",
-      "NEGATIVO 58 %\n"
-     ]
-    }
-   ],
    "source": [
     "#Test\n",
     "\n",
-    "#load model\n",
+    "#Load model\n",
     "from keras.models import load_model\n",
     "from keras.preprocessing.sequence import pad_sequences\n",
     "from keras.preprocessing.text import Tokenizer\n",
-    "from keras.preprocessing.text import Tokenizer\n",
     "\n",
-    "loaded_model = load_model('sentiment_dfngt.keras')\n",
+    "loaded_model = load_model('model.keras')\n",
     "\n",
     "sentence = input(\"Enter the sentence: \")\n",
     "sequence = preprocess_text(sentence)\n",
@@ -429,7 +210,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.5"
+   "version": "2.7.18"
   },
   "orig_nbformat": 4
  },