From c54dddb759784ce204c4fb8630aec63f27de5cc4 Mon Sep 17 00:00:00 2001 From: Stremmel Date: Fri, 2 Mar 2018 14:46:46 -0600 Subject: [PATCH] fixed y label on accuracy plot to say "accuracy" instead of "loss" --- 3.5-classifying-movie-reviews.ipynb | 482 +++------------------------- 1 file changed, 37 insertions(+), 445 deletions(-) diff --git a/3.5-classifying-movie-reviews.ipynb b/3.5-classifying-movie-reviews.ipynb index 1d445a7ff2..2bfe77fcfa 100644 --- a/3.5-classifying-movie-reviews.ipynb +++ b/3.5-classifying-movie-reviews.ipynb @@ -2,20 +2,9 @@ "cells": [ { "cell_type": "code", - "execution_count": 20, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "'2.0.8'" - ] - }, - "execution_count": 20, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "import keras\n", "keras.__version__" @@ -61,7 +50,7 @@ }, { "cell_type": "code", - "execution_count": 21, + "execution_count": null, "metadata": { "collapsed": true }, @@ -86,257 +75,18 @@ }, { "cell_type": "code", - "execution_count": 22, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "[1,\n", - " 14,\n", - " 22,\n", - " 16,\n", - " 43,\n", - " 530,\n", - " 973,\n", - " 1622,\n", - " 1385,\n", - " 65,\n", - " 458,\n", - " 4468,\n", - " 66,\n", - " 3941,\n", - " 4,\n", - " 173,\n", - " 36,\n", - " 256,\n", - " 5,\n", - " 25,\n", - " 100,\n", - " 43,\n", - " 838,\n", - " 112,\n", - " 50,\n", - " 670,\n", - " 2,\n", - " 9,\n", - " 35,\n", - " 480,\n", - " 284,\n", - " 5,\n", - " 150,\n", - " 4,\n", - " 172,\n", - " 112,\n", - " 167,\n", - " 2,\n", - " 336,\n", - " 385,\n", - " 39,\n", - " 4,\n", - " 172,\n", - " 4536,\n", - " 1111,\n", - " 17,\n", - " 546,\n", - " 38,\n", - " 13,\n", - " 447,\n", - " 4,\n", - " 192,\n", - " 50,\n", - " 16,\n", - " 6,\n", - " 147,\n", - " 2025,\n", - " 19,\n", - " 14,\n", - " 22,\n", - " 4,\n", - " 1920,\n", - " 4613,\n", - " 469,\n", - " 4,\n", - " 22,\n", - " 71,\n", - " 87,\n", - " 12,\n", - " 16,\n", - " 43,\n", - " 530,\n", - " 38,\n", - " 76,\n", - " 15,\n", - " 13,\n", - " 1247,\n", - " 4,\n", - " 22,\n", - " 17,\n", - " 515,\n", - " 17,\n", - " 12,\n", - " 16,\n", - " 626,\n", - " 18,\n", - " 2,\n", - " 5,\n", - " 62,\n", - " 386,\n", - " 12,\n", - " 8,\n", - " 316,\n", - " 8,\n", - " 106,\n", - " 5,\n", - " 4,\n", - " 2223,\n", - " 5244,\n", - " 16,\n", - " 480,\n", - " 66,\n", - " 3785,\n", - " 33,\n", - " 4,\n", - " 130,\n", - " 12,\n", - " 16,\n", - " 38,\n", - " 619,\n", - " 5,\n", - " 25,\n", - " 124,\n", - " 51,\n", - " 36,\n", - " 135,\n", - " 48,\n", - " 25,\n", - " 1415,\n", - " 33,\n", - " 6,\n", - " 22,\n", - " 12,\n", - " 215,\n", - " 28,\n", - " 77,\n", - " 52,\n", - " 5,\n", - " 14,\n", - " 407,\n", - " 16,\n", - " 82,\n", - " 2,\n", - " 8,\n", - " 4,\n", - " 107,\n", - " 117,\n", - " 5952,\n", - " 15,\n", - " 256,\n", - " 4,\n", - " 2,\n", - " 7,\n", - " 3766,\n", - " 5,\n", - " 723,\n", - " 36,\n", - " 71,\n", - " 43,\n", - " 530,\n", - " 476,\n", - " 26,\n", - " 400,\n", - " 317,\n", - " 46,\n", - " 7,\n", - " 4,\n", - " 2,\n", - " 1029,\n", - " 13,\n", - " 104,\n", - " 88,\n", - " 4,\n", - " 381,\n", - " 15,\n", - " 297,\n", - " 98,\n", - " 32,\n", - " 2071,\n", - " 56,\n", - " 26,\n", - " 141,\n", - " 6,\n", - " 194,\n", - " 7486,\n", - " 18,\n", - " 4,\n", - " 226,\n", - " 22,\n", - " 21,\n", - " 134,\n", - " 476,\n", - " 26,\n", - " 480,\n", - " 5,\n", - " 144,\n", - " 30,\n", - " 5535,\n", - " 18,\n", - " 51,\n", - " 36,\n", - " 28,\n", - " 224,\n", - " 92,\n", - " 25,\n", - " 104,\n", - " 4,\n", - " 226,\n", - " 65,\n", - " 16,\n", - " 38,\n", - " 1334,\n", - " 88,\n", - " 12,\n", - " 16,\n", - " 283,\n", - " 5,\n", - " 16,\n", - " 4472,\n", - " 113,\n", - " 103,\n", - " 32,\n", - " 15,\n", - " 16,\n", - " 5345,\n", - " 19,\n", - " 178,\n", - " 32]" - ] - }, - "execution_count": 22, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "train_data[0]" ] }, { "cell_type": "code", - "execution_count": 23, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "1" - ] - }, - "execution_count": 23, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "train_labels[0]" ] @@ -350,20 +100,9 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "9999" - ] - }, - "execution_count": 24, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "max([max(sequence) for sequence in train_data])" ] @@ -377,7 +116,7 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": null, "metadata": { "collapsed": true }, @@ -394,20 +133,9 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "\"? this film was just brilliant casting location scenery story direction everyone's really suited the part they played and you could just imagine being there robert ? is an amazing actor and now the same being director ? father came from the same scottish island as myself so i loved the fact there was a real connection with this film the witty remarks throughout the film were great it was just brilliant so much that i bought the film as soon as it was released for ? and would recommend it to everyone to watch and the fly fishing was amazing really cried at the end it was so sad and you know what they say if you cry at a film it must have been good and this definitely was also ? to the two little boy's that played the ? of norman and paul they were just brilliant children are often left out of the ? list i think because the stars that play them all grown up are such a big profile for the whole film but these children are amazing and should be praised for what they have done don't you think the whole story was so lovely because it was true and was someone's life after all that was shared with us all\"" - ] - }, - "execution_count": 26, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "decoded_review" ] @@ -433,7 +161,7 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": null, "metadata": { "collapsed": true }, @@ -463,20 +191,9 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "array([ 0., 1., 1., ..., 0., 0., 0.])" - ] - }, - "execution_count": 28, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "x_train[0]" ] @@ -490,7 +207,7 @@ }, { "cell_type": "code", - "execution_count": 29, + "execution_count": null, "metadata": { "collapsed": true }, @@ -566,7 +283,7 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": null, "metadata": { "collapsed": true }, @@ -598,7 +315,7 @@ }, { "cell_type": "code", - "execution_count": 31, + "execution_count": null, "metadata": { "collapsed": true }, @@ -620,7 +337,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": null, "metadata": { "collapsed": true }, @@ -642,7 +359,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": null, "metadata": { "collapsed": true }, @@ -668,7 +385,7 @@ }, { "cell_type": "code", - "execution_count": 32, + "execution_count": null, "metadata": { "collapsed": true }, @@ -694,57 +411,9 @@ }, { "cell_type": "code", - "execution_count": 33, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Train on 15000 samples, validate on 10000 samples\n", - "Epoch 1/20\n", - "15000/15000 [==============================] - 1s - loss: 0.5103 - acc: 0.7911 - val_loss: 0.4016 - val_acc: 0.8628\n", - "Epoch 2/20\n", - "15000/15000 [==============================] - 1s - loss: 0.3110 - acc: 0.9031 - val_loss: 0.3085 - val_acc: 0.8870\n", - "Epoch 3/20\n", - "15000/15000 [==============================] - 1s - loss: 0.2309 - acc: 0.9235 - val_loss: 0.2803 - val_acc: 0.8908\n", - "Epoch 4/20\n", - "15000/15000 [==============================] - 1s - loss: 0.1795 - acc: 0.9428 - val_loss: 0.2735 - val_acc: 0.8893\n", - "Epoch 5/20\n", - "15000/15000 [==============================] - 1s - loss: 0.1475 - acc: 0.9526 - val_loss: 0.2788 - val_acc: 0.8890\n", - "Epoch 6/20\n", - "15000/15000 [==============================] - 1s - loss: 0.1185 - acc: 0.9638 - val_loss: 0.3330 - val_acc: 0.8764\n", - "Epoch 7/20\n", - "15000/15000 [==============================] - 1s - loss: 0.1005 - acc: 0.9703 - val_loss: 0.3055 - val_acc: 0.8838\n", - "Epoch 8/20\n", - "15000/15000 [==============================] - 1s - loss: 0.0818 - acc: 0.9773 - val_loss: 0.3344 - val_acc: 0.8769\n", - "Epoch 9/20\n", - "15000/15000 [==============================] - 1s - loss: 0.0696 - acc: 0.9814 - val_loss: 0.3607 - val_acc: 0.8800\n", - "Epoch 10/20\n", - "15000/15000 [==============================] - 1s - loss: 0.0547 - acc: 0.9873 - val_loss: 0.3776 - val_acc: 0.8785\n", - "Epoch 11/20\n", - "15000/15000 [==============================] - 1s - loss: 0.0453 - acc: 0.9895 - val_loss: 0.4035 - val_acc: 0.8765\n", - "Epoch 12/20\n", - "15000/15000 [==============================] - 1s - loss: 0.0353 - acc: 0.9930 - val_loss: 0.4437 - val_acc: 0.8766\n", - "Epoch 13/20\n", - "15000/15000 [==============================] - 1s - loss: 0.0269 - acc: 0.9956 - val_loss: 0.4637 - val_acc: 0.8747\n", - "Epoch 14/20\n", - "15000/15000 [==============================] - 1s - loss: 0.0212 - acc: 0.9968 - val_loss: 0.4877 - val_acc: 0.8714\n", - "Epoch 15/20\n", - "15000/15000 [==============================] - 1s - loss: 0.0162 - acc: 0.9977 - val_loss: 0.6080 - val_acc: 0.8625\n", - "Epoch 16/20\n", - "15000/15000 [==============================] - 1s - loss: 0.0115 - acc: 0.9993 - val_loss: 0.5778 - val_acc: 0.8698\n", - "Epoch 17/20\n", - "15000/15000 [==============================] - 1s - loss: 0.0116 - acc: 0.9979 - val_loss: 0.5906 - val_acc: 0.8702\n", - "Epoch 18/20\n", - "15000/15000 [==============================] - 1s - loss: 0.0054 - acc: 0.9998 - val_loss: 0.6204 - val_acc: 0.8639\n", - "Epoch 19/20\n", - "15000/15000 [==============================] - 1s - loss: 0.0083 - acc: 0.9984 - val_loss: 0.6419 - val_acc: 0.8676\n", - "Epoch 20/20\n", - "15000/15000 [==============================] - 1s - loss: 0.0031 - acc: 0.9998 - val_loss: 0.6796 - val_acc: 0.8683\n" - ] - } - ], + "outputs": [], "source": [ "history = model.fit(partial_x_train,\n", " partial_y_train,\n", @@ -766,20 +435,9 @@ }, { "cell_type": "code", - "execution_count": 34, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "dict_keys(['val_acc', 'acc', 'val_loss', 'loss'])" - ] - }, - "execution_count": 34, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "history_dict = history.history\n", "history_dict.keys()" @@ -795,20 +453,9 @@ }, { "cell_type": "code", - "execution_count": 36, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYUAAAEWCAYAAACJ0YulAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "import matplotlib.pyplot as plt\n", "\n", @@ -833,20 +480,9 @@ }, { "cell_type": "code", - "execution_count": 38, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYsAAAEWCAYAAACXGLsWAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "plt.clf() # clear figure\n", "acc_values = history_dict['acc']\n", @@ -856,7 +492,7 @@ "plt.plot(epochs, val_acc, 'b', label='Validation acc')\n", "plt.title('Training and validation accuracy')\n", "plt.xlabel('Epochs')\n", - "plt.ylabel('Loss')\n", + "plt.ylabel('Accuracy')\n", "plt.legend()\n", "\n", "plt.show()" @@ -885,25 +521,9 @@ }, { "cell_type": "code", - "execution_count": 40, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 1/4\n", - "25000/25000 [==============================] - 1s - loss: 0.4738 - acc: 0.8044 \n", - "Epoch 2/4\n", - "25000/25000 [==============================] - 1s - loss: 0.2660 - acc: 0.9076 \n", - "Epoch 3/4\n", - "25000/25000 [==============================] - 1s - loss: 0.2028 - acc: 0.9277 \n", - "Epoch 4/4\n", - "25000/25000 [==============================] - 1s - loss: 0.1700 - acc: 0.9397 \n", - "24544/25000 [============================>.] - ETA: 0s" - ] - } - ], + "outputs": [], "source": [ "model = models.Sequential()\n", "model.add(layers.Dense(16, activation='relu', input_shape=(10000,)))\n", @@ -920,20 +540,9 @@ }, { "cell_type": "code", - "execution_count": 41, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "[0.29184698499679568, 0.88495999999999997]" - ] - }, - "execution_count": 41, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "results" ] @@ -957,26 +566,9 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "array([[ 0.91966152],\n", - " [ 0.86563045],\n", - " [ 0.99936908],\n", - " ..., \n", - " [ 0.45731062],\n", - " [ 0.0038014 ],\n", - " [ 0.79525089]], dtype=float32)" - ] - }, - "execution_count": 26, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "model.predict(x_test)" ] @@ -1043,7 +635,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.5.2" + "version": "3.6.2" } }, "nbformat": 4,