Add files via upload

Bidirectioanl GRU.ipynb

@@ -0,0 +1,126 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Bidirectional GRU"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from __future__ import print_function\n",
+    "from sklearn.cross_validation import train_test_split\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "np.random.seed(1337)  # for reproducibility\n",
+    "from keras.preprocessing import sequence\n",
+    "from keras.utils import np_utils\n",
+    "from keras.models import Sequential\n",
+    "from keras.layers import Dense, Dropout, Activation, Embedding\n",
+    "from keras.layers import Dense, Dropout, Embedding, LSTM, Input, Bidirectional\n",
+    "from keras.datasets import imdb\n",
+    "from keras.utils.np_utils import to_categorical\n",
+    "from sklearn.metrics import (precision_score, recall_score,\n",
+    "                             f1_score, accuracy_score,mean_squared_error,mean_absolute_error)\n",
+    "from sklearn import metrics\n",
+    "from sklearn.preprocessing import Normalizer\n",
+    "import h5py\n",
+    "from keras import callbacks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dataset = np.loadtxt(\"pima-indians-diabetes.csv\", delimiter=\",\")\n",
+    "# split into input (X) and output (Y) variables\n",
+    "X = dataset[:,0:8]\n",
+    "Y = dataset[:,8]\n",
+    "\n",
+    "#normalize the data\n",
+    "scaler = Normalizer().fit(X)\n",
+    "X = scaler.transform(X)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.33, random_state=42)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# reshape input to be [samples, time steps, features]\n",
+    "X_train = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))\n",
+    "X_test = np.reshape(testT, (testT.shape[0], 1, testT.shape[1]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 1. define the network\n",
+    "model = Sequential()\n",
+    "model.add(Bidirectional(GRU(4),input_shape=(1, 8)))\n",
+    "model.add(Dropout(0.1))\n",
+    "model.add(Dense(1))\n",
+    "model.add(Activation('sigmoid'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# try using different optimizers and different optimizer configs\n",
+    "model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])\n",
+    "checkpointer = callbacks.ModelCheckpoint(filepath=\"logs/bidirectioanl-gru/checkpoint-{epoch:02d}.hdf5\", verbose=1, save_best_only=True, monitor='val_acc',mode='max')\n",
+    "model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=1000, validation_data=(X_test, y_test),callbacks=[checkpointer])\n",
+    "model.save(\"logs/bidirectioanl-gru/lstm1layer_model.hdf5\")\n",
+    "\n",
+    "loss, accuracy = model.evaluate(X_test, y_test)\n",
+    "print(\"\\nLoss: %.2f, Accuracy: %.2f%%\" % (loss, accuracy*100))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "securetensor",
+   "language": "python",
+   "name": "securetensor"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

Bidirectional-LSTM.ipynb

@@ -0,0 +1,126 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Bidirectional LSTM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from __future__ import print_function\n",
+    "from sklearn.cross_validation import train_test_split\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "np.random.seed(1337)  # for reproducibility\n",
+    "from keras.preprocessing import sequence\n",
+    "from keras.utils import np_utils\n",
+    "from keras.models import Sequential\n",
+    "from keras.layers import Dense, Dropout, Activation, Embedding\n",
+    "from keras.layers import Dense, Dropout, Embedding, LSTM, Input, Bidirectional\n",
+    "from keras.datasets import imdb\n",
+    "from keras.utils.np_utils import to_categorical\n",
+    "from sklearn.metrics import (precision_score, recall_score,\n",
+    "                             f1_score, accuracy_score,mean_squared_error,mean_absolute_error)\n",
+    "from sklearn import metrics\n",
+    "from sklearn.preprocessing import Normalizer\n",
+    "import h5py\n",
+    "from keras import callbacks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dataset = np.loadtxt(\"pima-indians-diabetes.csv\", delimiter=\",\")\n",
+    "# split into input (X) and output (Y) variables\n",
+    "X = dataset[:,0:8]\n",
+    "Y = dataset[:,8]\n",
+    "\n",
+    "#normalize the data\n",
+    "scaler = Normalizer().fit(X)\n",
+    "X = scaler.transform(X)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.33, random_state=42)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# reshape input to be [samples, time steps, features]\n",
+    "X_train = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))\n",
+    "X_test = np.reshape(testT, (testT.shape[0], 1, testT.shape[1]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 1. define the network\n",
+    "model = Sequential()\n",
+    "model.add(Bidirectional(LSTM(4),input_shape=(1, 8)))\n",
+    "model.add(Dropout(0.1))\n",
+    "model.add(Dense(1))\n",
+    "model.add(Activation('sigmoid'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# try using different optimizers and different optimizer configs\n",
+    "model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])\n",
+    "checkpointer = callbacks.ModelCheckpoint(filepath=\"logs/bidirectioanl-lstm/checkpoint-{epoch:02d}.hdf5\", verbose=1, save_best_only=True, monitor='val_acc',mode='max')\n",
+    "model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=1000, validation_data=(X_test, y_test),callbacks=[checkpointer])\n",
+    "model.save(\"logs/bidirectioanl-lstm/lstm1layer_model.hdf5\")\n",
+    "\n",
+    "loss, accuracy = model.evaluate(X_test, y_test)\n",
+    "print(\"\\nLoss: %.2f, Accuracy: %.2f%%\" % (loss, accuracy*100))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "securetensor",
+   "language": "python",
+   "name": "securetensor"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

Bidirectional-RNN.ipynb

@@ -0,0 +1,126 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Bidirectioanl RNN"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from __future__ import print_function\n",
+    "from sklearn.cross_validation import train_test_split\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "np.random.seed(1337)  # for reproducibility\n",
+    "from keras.preprocessing import sequence\n",
+    "from keras.utils import np_utils\n",
+    "from keras.models import Sequential\n",
+    "from keras.layers import Dense, Dropout, Activation, Embedding\n",
+    "from keras.layers import Dense, Dropout, Embedding, LSTM, Input, Bidirectional\n",
+    "from keras.datasets import imdb\n",
+    "from keras.utils.np_utils import to_categorical\n",
+    "from sklearn.metrics import (precision_score, recall_score,\n",
+    "                             f1_score, accuracy_score,mean_squared_error,mean_absolute_error)\n",
+    "from sklearn import metrics\n",
+    "from sklearn.preprocessing import Normalizer\n",
+    "import h5py\n",
+    "from keras import callbacks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dataset = np.loadtxt(\"pima-indians-diabetes.csv\", delimiter=\",\")\n",
+    "# split into input (X) and output (Y) variables\n",
+    "X = dataset[:,0:8]\n",
+    "Y = dataset[:,8]\n",
+    "\n",
+    "#normalize the data\n",
+    "scaler = Normalizer().fit(X)\n",
+    "X = scaler.transform(X)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.33, random_state=42)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# reshape input to be [samples, time steps, features]\n",
+    "X_train = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))\n",
+    "X_test = np.reshape(testT, (testT.shape[0], 1, testT.shape[1]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 1. define the network\n",
+    "model = Sequential()\n",
+    "model.add(Bidirectional(SimpleRNN(4),input_shape=(1, 8)))\n",
+    "model.add(Dropout(0.1))\n",
+    "model.add(Dense(1))\n",
+    "model.add(Activation('sigmoid'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# try using different optimizers and different optimizer configs\n",
+    "model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])\n",
+    "checkpointer = callbacks.ModelCheckpoint(filepath=\"logs/bidirectioanl-rnn/checkpoint-{epoch:02d}.hdf5\", verbose=1, save_best_only=True, monitor='val_acc',mode='max')\n",
+    "model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=1000, validation_data=(X_test, y_test),callbacks=[checkpointer])\n",
+    "model.save(\"logs/bidirectioanl-rnn/lstm1layer_model.hdf5\")\n",
+    "\n",
+    "loss, accuracy = model.evaluate(X_test, y_test)\n",
+    "print(\"\\nLoss: %.2f, Accuracy: %.2f%%\" % (loss, accuracy*100))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "securetensor",
+   "language": "python",
+   "name": "securetensor"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}