add SVM, Adaboost, Random Forest and ANN
Esse commit está contido em:
matonglidewazi
+489
-6
@@ -29,14 +29,24 @@
|
|||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": 2,
|
"execution_count": 7,
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [],
|
"outputs": [],
|
||||||
"source": [
|
"source": [
|
||||||
"import numpy as np\n",
|
"import numpy as np\n",
|
||||||
"import pyeeg as pe\n",
|
"#import pyeeg as pe\n",
|
||||||
"import pickle as pickle\n",
|
"import pickle as pickle\n",
|
||||||
"import pandas as pd"
|
"import pandas as pd\n",
|
||||||
|
"import math\n",
|
||||||
|
"\n",
|
||||||
|
"from sklearn import svm\n",
|
||||||
|
"from sklearn.preprocessing import normalize\n",
|
||||||
|
"from sklearn.ensemble import RandomForestRegressor\n",
|
||||||
|
"from sklearn.ensemble import AdaBoostRegressor\n",
|
||||||
|
"\n",
|
||||||
|
"import os\n",
|
||||||
|
"#import tensorflow as tf\n",
|
||||||
|
"import time"
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
@@ -82,7 +92,7 @@
|
|||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": 62,
|
"execution_count": 60,
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [],
|
"outputs": [],
|
||||||
"source": [
|
"source": [
|
||||||
@@ -124,6 +134,38 @@
|
|||||||
" meta = np.array(meta)\n",
|
" meta = np.array(meta)\n",
|
||||||
" np.save('out\\s' + sub, meta, allow_pickle=True, fix_imports=True)\n",
|
" np.save('out\\s' + sub, meta, allow_pickle=True, fix_imports=True)\n",
|
||||||
"\n",
|
"\n",
|
||||||
|
"def testing (M, L, model):\n",
|
||||||
|
" '''\n",
|
||||||
|
" arguments: M: testing dataset\n",
|
||||||
|
" L: testing dataset label\n",
|
||||||
|
" model: scikit-learn model\n",
|
||||||
|
"\n",
|
||||||
|
" return: void\n",
|
||||||
|
" '''\n",
|
||||||
|
" output = model.predict(M[0:78080:32])\n",
|
||||||
|
" label = L[0:78080:32]\n",
|
||||||
|
"\n",
|
||||||
|
" k = 0\n",
|
||||||
|
" l = 0\n",
|
||||||
|
"\n",
|
||||||
|
" for i in range(len(label)):\n",
|
||||||
|
" k = k + (output[i] - label[i])*(output[i] - label[i]) #square difference \n",
|
||||||
|
"\n",
|
||||||
|
" #a good guess\n",
|
||||||
|
" if (output[i] > 5 and label[i] > 5):\n",
|
||||||
|
" l = l + 1\n",
|
||||||
|
" elif (output[i] < 5 and label[i] <5):\n",
|
||||||
|
" l = l + 1\n",
|
||||||
|
"\n",
|
||||||
|
" print (\"l2 error:\", k/len(label), \"classification accuracy:\", l / len(label),l, len(label))"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
"for subjects in subjectList:\n",
|
"for subjects in subjectList:\n",
|
||||||
" FFT_Processing (subjects, channel, band, window_size, step_size, sample_rate)"
|
" FFT_Processing (subjects, channel, band, window_size, step_size, sample_rate)"
|
||||||
]
|
]
|
||||||
@@ -133,7 +175,7 @@
|
|||||||
"metadata": {},
|
"metadata": {},
|
||||||
"source": [
|
"source": [
|
||||||
"## 3.Segment of preprocessed data\n",
|
"## 3.Segment of preprocessed data\n",
|
||||||
"* training dataset: 75.5%\n",
|
"* training dataset: 75 %\n",
|
||||||
"* validation dataset: 12.5%\n",
|
"* validation dataset: 12.5%\n",
|
||||||
"* testing dataset: 12.5%\n",
|
"* testing dataset: 12.5%\n",
|
||||||
"\n",
|
"\n",
|
||||||
@@ -204,12 +246,453 @@
|
|||||||
"print(\"validation dataset:\", np.array(data_validation).shape, np.array(label_validation).shape)"
|
"print(\"validation dataset:\", np.array(data_validation).shape, np.array(label_validation).shape)"
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## 4.Regression\n",
|
||||||
|
"### 0. Loading Training and Testing dataset"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 59,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"with open('out\\data_training.npy', 'rb') as fileTrain:\n",
|
||||||
|
" X = np.load(fileTrain)\n",
|
||||||
|
" \n",
|
||||||
|
"with open('out\\label_training.npy', 'rb') as fileTrainL:\n",
|
||||||
|
" Y = np.load(fileTrainL)\n",
|
||||||
|
" \n",
|
||||||
|
"X = normalize(X)\n",
|
||||||
|
"Z = np.ravel(Y[:, [1]])\n",
|
||||||
|
"\n",
|
||||||
|
"Arousal_Train = np.ravel(Y[:, [0]])\n",
|
||||||
|
"Valence_Train = np.ravel(Y[:, [1]])\n",
|
||||||
|
"Domain_Train = np.ravel(Y[:, [2]])\n",
|
||||||
|
"Like_Train = np.ravel(Y[:, [3]])\n",
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"with open('out\\data_validation.npy', 'rb') as fileTrain:\n",
|
||||||
|
" M = np.load(fileTrain)\n",
|
||||||
|
" \n",
|
||||||
|
"with open('out\\label_validation.npy', 'rb') as fileTrainL:\n",
|
||||||
|
" N = np.load(fileTrainL)\n",
|
||||||
|
"\n",
|
||||||
|
"M = normalize(M)\n",
|
||||||
|
"L = np.ravel(N[:, [1]])\n",
|
||||||
|
"\n",
|
||||||
|
"Arousal_Test = np.ravel(N[:, [0]])\n",
|
||||||
|
"Valence_Test = np.ravel(N[:, [1]])\n",
|
||||||
|
"Domain_Test = np.ravel(N[:, [2]])\n",
|
||||||
|
"Like_Test = np.ravel(N[:, [3]])"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"\n",
|
||||||
|
"### 1. Support Vector Regression\n",
|
||||||
|
"* default setting, l1 error: 1.621761042477756 classification error: 0.6057377049180328 1478 2440"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 15,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"SVR(C=1.0, cache_size=200, coef0=0.0, degree=3, epsilon=0.1, gamma='auto',\n",
|
||||||
|
" kernel='rbf', max_iter=-1, shrinking=True, tol=0.001, verbose=False)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 15,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"clf = svm.SVR()\n",
|
||||||
|
"clf.fit(X[0:468480:32], Z[0:468480:32]) "
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"### 2. Random Forest Regression\n",
|
||||||
|
"* n_estimators = 10, sample rate = 1/32, l1 error: 1.137919672131145 classification accuracy: 0.7774590163934426 1897 2440\n",
|
||||||
|
"* n_estimators = 100, sample rate = 1/32, l1 error: 1.1029040163934432 classification accuracy: 0.8147540983606557 1988 2440\n",
|
||||||
|
"* n_estimators = 100, min_samples_leaf=10, sample rate = 1/32, l1 error: 1.274458098574928 classification accuracy: 0.7622950819672131 1860 2440\n",
|
||||||
|
"* n_estimators = 100, min_samples_leaf=50, sample rate = 1/32, l1 error: 1.4575897309409926 classification accuracy: 0.6823770491803278 1665 2440\n",
|
||||||
|
"\n",
|
||||||
|
"* n_estimators = 250, sample rate = 1/32, l1 error: 1.0905590819672137 classification accuracy: 0.830327868852459 2026 2440\n",
|
||||||
|
"* n_estimators = 750, sample rate = 1/32, l1 error: 1.0953162021857932 classification accuracy: 0.8340163934426229 2035 2440\n",
|
||||||
|
"* n_estimators = 750, sample rate = 1/8, l1 error: l1 error: 1.066982950819674 classification accuracy: 0.8217213114754098 2005 2440\n",
|
||||||
|
"* __n_estimators = 512, sample rate = 1/32, l1 error: 1.092375304175206 classification accuracy: 0.8364754098360656 2041 2440\n",
|
||||||
|
"__\n",
|
||||||
|
"\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 62,
|
||||||
|
"metadata": {
|
||||||
|
"scrolled": true
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"l2 error: 1.876775658972537 classification accuracy: 0.8290983606557377 2023 2440\n"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"Val_R = RandomForestRegressor(n_estimators=512, n_jobs=6)\n",
|
||||||
|
"Val_R.fit(X[0:468480:32], Valence_Train[0:468480:32])\n",
|
||||||
|
"testing (M, Valence_Test, Val_R)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 63,
|
||||||
|
"metadata": {
|
||||||
|
"scrolled": true
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"l2 error: 2.0764509040715233 classification accuracy: 0.8266393442622951 2017 2440\n"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"Aro_R = RandomForestRegressor(n_estimators=512, n_jobs=6)\n",
|
||||||
|
"Aro_R.fit(X[0:468480:32], Arousal_Train[0:468480:32])\n",
|
||||||
|
"testing (M, Arousal_Test, Aro_R)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 64,
|
||||||
|
"metadata": {
|
||||||
|
"scrolled": true
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"l2 error: 1.813647083229937 classification accuracy: 0.8184426229508197 1997 2440\n"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"Dom_R = RandomForestRegressor(n_estimators=512, n_jobs=6)\n",
|
||||||
|
"Dom_R.fit(X[0:468480:32], Domain_Train[0:468480:32])\n",
|
||||||
|
"testing (M, Domain_Test, Dom_R)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 65,
|
||||||
|
"metadata": {
|
||||||
|
"scrolled": true
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"l2 error: 2.489005384276336 classification accuracy: 0.8512295081967213 2077 2440\n"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"Lik_R = RandomForestRegressor(n_estimators=512, n_jobs=6)\n",
|
||||||
|
"Lik_R.fit(X[0:468480:32], Like_Train[0:468480:32])\n",
|
||||||
|
"testing (M, Like_Test, Lik_R)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"### 3. AdaBoost Regression\n",
|
||||||
|
"* n = 50, lr = 1.0: l2 error: 3.8454054839726695 classification accuracy: 0.6147540983606558 1500 2440\n",
|
||||||
|
"* n = 50, lr = 1.0, square: l2 error: 4.015289218608164 classification accuracy: 0.5913934426229508 1443 2440\n",
|
||||||
|
"* n = 500, lr = 1.0: l2 error: 3.8861651269012594 classification accuracy: 0.6155737704918033 1502 2440\n",
|
||||||
|
"*\n",
|
||||||
|
"*"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 32,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"AdaBoostRegressor(base_estimator=None, learning_rate=0.01, loss='linear',\n",
|
||||||
|
" n_estimators=5000, random_state=None)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 32,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"clf = AdaBoostRegressor(n_estimators=5000, learning_rate=0.01)\n",
|
||||||
|
"clf.fit(X[0:468480:32], Z[0:468480:32])"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"### Calculating accuracy and loss"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 58,
|
||||||
|
"metadata": {
|
||||||
|
"scrolled": true
|
||||||
|
},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"l2 error: 1.8832017200301692 classification accuracy: 0.8348360655737705 2037 2440\n"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"output = Val_R.predict(M[0:78080:32])\n",
|
||||||
|
"label = L[0:78080:32]\n",
|
||||||
|
"\n",
|
||||||
|
"k = 0\n",
|
||||||
|
"l = 0\n",
|
||||||
|
"\n",
|
||||||
|
"for i in range(len(label)):\n",
|
||||||
|
" k = k + (output[i] - label[i])*(output[i] - label[i]) #square difference \n",
|
||||||
|
" \n",
|
||||||
|
" #a good guess\n",
|
||||||
|
" if (output[i] > 5 and label[i] > 5):\n",
|
||||||
|
" l = l + 1\n",
|
||||||
|
" elif (output[i] < 5 and label[i] <5):\n",
|
||||||
|
" l = l + 1\n",
|
||||||
|
"\n",
|
||||||
|
"print (\"l2 error:\", k/len(label), \"classification accuracy:\", l / len(label),l, len(label))"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"### 4. ANN\n",
|
||||||
|
"* 500 epoch 0.005 128 - 256 - 256 - 128 loss = 3.1\n",
|
||||||
|
"* 3000 epoch 0.0001 256-512-512-256 Epoch: 3196 - Training Cost: 1.8372873067855835 Testing Cost: 2.231332540512085\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": null,
|
"execution_count": null,
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [],
|
"outputs": [],
|
||||||
"source": []
|
"source": [
|
||||||
|
"# Pull out columns for X (data to train with) and Y (value to predict)\n",
|
||||||
|
"X_training = X[0:468480:32]\n",
|
||||||
|
"Y_training = Z[0:468480:32]\n",
|
||||||
|
"\n",
|
||||||
|
"# Pull out columns for X (data to train with) and Y (value to predict)\n",
|
||||||
|
"X_testing = M[0:78080:32]\n",
|
||||||
|
"Y_testing = L[0:78080:32]\n",
|
||||||
|
"\n",
|
||||||
|
"# DO Scale both the training inputs and outputs\n",
|
||||||
|
"X_scaled_training = pd.DataFrame (data = X_training).values\n",
|
||||||
|
"Y_scaled_training = pd.DataFrame (data = Y_training).values\n",
|
||||||
|
"\n",
|
||||||
|
"# It's very important that the training and test data are scaled with the same scaler.\n",
|
||||||
|
"X_scaled_testing = pd.DataFrame (data = X_testing).values\n",
|
||||||
|
"Y_scaled_testing = pd.DataFrame (data = Y_testing).values"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"# Turn off TensorFlow warning messages in program output\n",
|
||||||
|
"os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'\n",
|
||||||
|
"\n",
|
||||||
|
"# Define model parameters\n",
|
||||||
|
"t = time.time()\n",
|
||||||
|
"learning_rate = 0.0001\n",
|
||||||
|
"training_epochs = 5000\n",
|
||||||
|
"display_step = 1\n",
|
||||||
|
"\n",
|
||||||
|
"# Define how many inputs and outputs are in our neural network\n",
|
||||||
|
"number_of_inputs = 70\n",
|
||||||
|
"number_of_outputs = 1\n",
|
||||||
|
"\n",
|
||||||
|
"# Define how many neurons we want in each layer of our neural network\n",
|
||||||
|
"layer_1_nodes = 512\n",
|
||||||
|
"layer_2_nodes = 1024\n",
|
||||||
|
"layer_3_nodes = 1024\n",
|
||||||
|
"layer_4_nodes = 512\n",
|
||||||
|
"\n",
|
||||||
|
"# Section One: Define the layers of the neural network itself\n",
|
||||||
|
"RUN_NAME = str(int(round(t * 1000))) + '_' + str(layer_1_nodes) + '_' + str(layer_2_nodes) + '_' + str(layer_3_nodes) + '_' + str(layer_4_nodes) + '_' + str(learning_rate) + '_' + str(training_epochs) + '_' + 'Val'\n",
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"# Input Layer\n",
|
||||||
|
"with tf.variable_scope('input'):\n",
|
||||||
|
" X = tf.placeholder(tf.float32, shape=(None, number_of_inputs))\n",
|
||||||
|
"\n",
|
||||||
|
"# Layer 1\n",
|
||||||
|
"with tf.variable_scope('layer_1'):\n",
|
||||||
|
" weights = tf.get_variable(\"weights1\", shape=[number_of_inputs, layer_1_nodes], initializer=tf.contrib.layers.xavier_initializer())\n",
|
||||||
|
" biases = tf.get_variable(name=\"biases1\", shape=[layer_1_nodes], initializer=tf.zeros_initializer())\n",
|
||||||
|
" layer_1_output = tf.nn.relu(tf.matmul(X, weights) + biases)\n",
|
||||||
|
"\n",
|
||||||
|
"# Layer 2\n",
|
||||||
|
"with tf.variable_scope('layer_2'):\n",
|
||||||
|
" weights = tf.get_variable(\"weights2\", shape=[layer_1_nodes, layer_2_nodes], initializer=tf.contrib.layers.xavier_initializer())\n",
|
||||||
|
" biases = tf.get_variable(name=\"biases2\", shape=[layer_2_nodes], initializer=tf.zeros_initializer())\n",
|
||||||
|
" layer_2_output = tf.nn.relu(tf.matmul(layer_1_output, weights) + biases)\n",
|
||||||
|
"\n",
|
||||||
|
"# Layer 3\n",
|
||||||
|
"with tf.variable_scope('layer_3'):\n",
|
||||||
|
" weights = tf.get_variable(\"weights3\", shape=[layer_2_nodes, layer_3_nodes], initializer=tf.contrib.layers.xavier_initializer())\n",
|
||||||
|
" biases = tf.get_variable(name=\"biases3\", shape=[layer_3_nodes], initializer=tf.zeros_initializer())\n",
|
||||||
|
" layer_3_output = tf.nn.relu(tf.matmul(layer_2_output, weights) + biases)\n",
|
||||||
|
"\n",
|
||||||
|
"# Layer 4\n",
|
||||||
|
"with tf.variable_scope('layer_4'):\n",
|
||||||
|
" weights = tf.get_variable(\"weights4\", shape=[layer_3_nodes, layer_4_nodes], initializer=tf.contrib.layers.xavier_initializer())\n",
|
||||||
|
" biases = tf.get_variable(name=\"biases4\", shape=[layer_4_nodes], initializer=tf.zeros_initializer())\n",
|
||||||
|
" layer_4_output = tf.nn.relu(tf.matmul(layer_3_output, weights) + biases)\n",
|
||||||
|
"\n",
|
||||||
|
"# Output Layer\n",
|
||||||
|
"with tf.variable_scope('output'):\n",
|
||||||
|
" weights = tf.get_variable(\"weights5\", shape=[layer_4_nodes, number_of_outputs], initializer=tf.contrib.layers.xavier_initializer())\n",
|
||||||
|
" biases = tf.get_variable(name=\"biases5\", shape=[number_of_outputs], initializer=tf.zeros_initializer())\n",
|
||||||
|
" prediction = tf.matmul(layer_4_output, weights) + biases\n",
|
||||||
|
"\n",
|
||||||
|
"# Section Two: Define the cost function of the neural network that will be optimized during training\n",
|
||||||
|
"\n",
|
||||||
|
"with tf.variable_scope('cost'):\n",
|
||||||
|
" Y = tf.placeholder(tf.float32, shape=(None, 1))\n",
|
||||||
|
" cost = tf.reduce_mean(tf.squared_difference(prediction, Y))\n",
|
||||||
|
"\n",
|
||||||
|
"# Section Three: Define the optimizer function that will be run to optimize the neural network\n",
|
||||||
|
"\n",
|
||||||
|
"with tf.variable_scope('train'):\n",
|
||||||
|
" optimizer = tf.train.AdamOptimizer(learning_rate).minimize(cost)\n",
|
||||||
|
"\n",
|
||||||
|
"# Create a summary operation to log the progress of the network\n",
|
||||||
|
"with tf.variable_scope('logging'):\n",
|
||||||
|
" tf.summary.scalar('current_cost', cost)\n",
|
||||||
|
" summary = tf.summary.merge_all()\n",
|
||||||
|
"\n",
|
||||||
|
"saver = tf.train.Saver()\n",
|
||||||
|
"\n",
|
||||||
|
"# Initialize a session so that we can run TensorFlow operations\n",
|
||||||
|
"with tf.Session() as session:\n",
|
||||||
|
"\n",
|
||||||
|
" # Run the global variable initializer to initialize all variables and layers of the neural network\n",
|
||||||
|
" session.run(tf.global_variables_initializer())\n",
|
||||||
|
"\n",
|
||||||
|
" # Create log file writers to record training progress.\n",
|
||||||
|
" # We'll store training and testing log data separately.\n",
|
||||||
|
" training_writer = tf.summary.FileWriter(\"./{}/logs/training\".format(RUN_NAME), session.graph)\n",
|
||||||
|
" testing_writer = tf.summary.FileWriter(\"./{}/logs/testing\".format(RUN_NAME), session.graph)\n",
|
||||||
|
"\n",
|
||||||
|
" # Run the optimizer over and over to train the network.\n",
|
||||||
|
" # One epoch is one full run through the training data set.\n",
|
||||||
|
" for epoch in range(training_epochs):\n",
|
||||||
|
"\n",
|
||||||
|
" # Feed in the training data and do one step of neural network training\n",
|
||||||
|
" session.run(optimizer, feed_dict={X: X_scaled_training, Y: Y_scaled_training})\n",
|
||||||
|
"\n",
|
||||||
|
" # Every few training steps, log our progress\n",
|
||||||
|
" if epoch % display_step == 0:\n",
|
||||||
|
" # Get the current accuracy scores by running the \"cost\" operation on the training and test data sets\n",
|
||||||
|
" training_cost, training_summary = session.run([cost, summary], feed_dict={X: X_scaled_training, Y:Y_scaled_training})\n",
|
||||||
|
" testing_cost, testing_summary = session.run([cost, summary], feed_dict={X: X_scaled_testing, Y:Y_scaled_testing})\n",
|
||||||
|
"\n",
|
||||||
|
" # Write the current training status to the log files (Which we can view with TensorBoard)\n",
|
||||||
|
" training_writer.add_summary(training_summary, epoch)\n",
|
||||||
|
" testing_writer.add_summary(testing_summary, epoch)\n",
|
||||||
|
"\n",
|
||||||
|
" # Print the current training status to the screen\n",
|
||||||
|
" print(\"Epoch: {} - Training Cost: {} Testing Cost: {}\".format(epoch, training_cost, testing_cost))\n",
|
||||||
|
"\n",
|
||||||
|
" # Training is now complete!\n",
|
||||||
|
"\n",
|
||||||
|
" # Get the final accuracy scores by running the \"cost\" operation on the training and test data sets\n",
|
||||||
|
" final_training_cost = session.run(cost, feed_dict={X: X_scaled_training, Y: Y_scaled_training})\n",
|
||||||
|
" final_testing_cost = session.run(cost, feed_dict={X: X_scaled_testing, Y: Y_scaled_testing})\n",
|
||||||
|
"\n",
|
||||||
|
" print(\"Final Training cost: {}\".format(final_training_cost))\n",
|
||||||
|
" print(\"Final Testing cost: {}\".format(final_testing_cost))\n",
|
||||||
|
"\n",
|
||||||
|
" save_path = saver.save(session, \"./{}/logs/trained_model.ckpt\".format(RUN_NAME))\n",
|
||||||
|
" print(\"Model saved: {}\".format(save_path))\n",
|
||||||
|
"\n",
|
||||||
|
" '''\n",
|
||||||
|
" # Now that the neural network is trained, let's use it to make predictions for our test data.\n",
|
||||||
|
" # Pass in the X testing data and run the \"prediciton\" operation\n",
|
||||||
|
" Y_predicted_scaled = session.run(prediction, feed_dict={X: X_scaled_testing})\n",
|
||||||
|
" # Unscale the data back to it's original units (dollars)\n",
|
||||||
|
" Y_predicted = Y_scaler.inverse_transform(Y_predicted_scaled)\n",
|
||||||
|
" real_earnings = test_data_df['total_earnings'].values[0]\n",
|
||||||
|
" predicted_earnings = Y_predicted[0][0]\n",
|
||||||
|
" print(\"The actual earnings of Game #1 were ${}\".format(real_earnings))\n",
|
||||||
|
" print(\"Our neural network predicted earnings of ${}\".format(predicted_earnings))\n",
|
||||||
|
" \n",
|
||||||
|
"'''\n",
|
||||||
|
" model_builder = tf.saved_model.builder.SavedModelBuilder(\"./{}/exported_model\".format(RUN_NAME))\n",
|
||||||
|
"\n",
|
||||||
|
" inputs = {\n",
|
||||||
|
" 'input': tf.saved_model.utils.build_tensor_info(X)\n",
|
||||||
|
" }\n",
|
||||||
|
" outputs = {\n",
|
||||||
|
" 'earnings': tf.saved_model.utils.build_tensor_info(prediction)\n",
|
||||||
|
" }\n",
|
||||||
|
"\n",
|
||||||
|
" signature_def = tf.saved_model.signature_def_utils.build_signature_def(\n",
|
||||||
|
" inputs=inputs,\n",
|
||||||
|
" outputs=outputs,\n",
|
||||||
|
" method_name=tf.saved_model.signature_constants.PREDICT_METHOD_NAME\n",
|
||||||
|
" )\n",
|
||||||
|
"\n",
|
||||||
|
" model_builder.add_meta_graph_and_variables(\n",
|
||||||
|
" session,\n",
|
||||||
|
" tags=[tf.saved_model.tag_constants.SERVING],\n",
|
||||||
|
" signature_def_map={\n",
|
||||||
|
" tf.saved_model.signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY: signature_def\n",
|
||||||
|
" }\n",
|
||||||
|
" )\n",
|
||||||
|
"\n",
|
||||||
|
" model_builder.save()\n",
|
||||||
|
" print('model saved')\n"
|
||||||
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
|
|||||||
Referência em uma Nova Issue
Bloquear um usuário