{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# E20- Neural Networks in Keras "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Use keras framework to solve the below exercises.\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Using TensorFlow backend.\n"
]
}
],
"source": [
"import numpy as np\n",
"import keras \n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 20.1 Predicting Student Admissions with Neural Networks\n",
"\n",
"In this notebook, we predict student admissions to graduate schools based on six pieces of data:\n",
"\n",
"1. GRE Scores (Test)\n",
"2. TOEFL Scores (Test)\n",
"3. University Ranking (1-5)\n",
"4. Statement of Purpose (SOP) and Letter of Recommendation Strength ( out of 5 )\n",
"5. Undergraduate GPA Scores (Grades)\n",
"6. Research Experience ( either 0 or 1 )\n",
"\n",
"**Exercise:** Design and train a shallow neural network to predict the chance of Admission for each entry. Choose the number of hidden layer and neurons that minimizes the error. "
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" GRE Score \n",
" TOEFL Score \n",
" University Rating \n",
" SOP \n",
" LOR \n",
" CGPA \n",
" Research \n",
" Chance of Admit \n",
" \n",
" \n",
" Serial No. \n",
" \n",
" \n",
" \n",
" \n",
" 1 \n",
" 337 \n",
" 118 \n",
" 4 \n",
" 4.5 \n",
" 4.5 \n",
" 9.65 \n",
" 1 \n",
" 0.92 \n",
" \n",
" \n",
" 2 \n",
" 324 \n",
" 107 \n",
" 4 \n",
" 4.0 \n",
" 4.5 \n",
" 8.87 \n",
" 1 \n",
" 0.76 \n",
" \n",
" \n",
" 3 \n",
" 316 \n",
" 104 \n",
" 3 \n",
" 3.0 \n",
" 3.5 \n",
" 8.00 \n",
" 1 \n",
" 0.72 \n",
" \n",
" \n",
" 4 \n",
" 322 \n",
" 110 \n",
" 3 \n",
" 3.5 \n",
" 2.5 \n",
" 8.67 \n",
" 1 \n",
" 0.80 \n",
" \n",
" \n",
" 5 \n",
" 314 \n",
" 103 \n",
" 2 \n",
" 2.0 \n",
" 3.0 \n",
" 8.21 \n",
" 0 \n",
" 0.65 \n",
" \n",
" \n",
"
\n",
"
"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"# Create moons dataset.\n",
"\n",
"from sklearn.datasets.samples_generator import make_moons\n",
"\n",
"x_train, y_train = make_moons(n_samples=1000, noise= 0.2, random_state=3)\n",
"plt.figure(figsize=(12, 8))\n",
"plt.scatter(x_train[:, 0], x_train[:,1], c=y_train, s=40, cmap=plt.cm.Spectral);"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Hint:** Use the next function to plt the decision boundary,"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"model = 'Sequential neural network in keras'\n",
"\n",
"def plot_decision_region(model, X, pred_fun):\n",
" min_x = np.min(X[:, 0])\n",
" max_x = np.max(X[:, 0])\n",
" min_y = np.min(X[:, 1])\n",
" max_y = np.max(X[:, 1])\n",
" min_x = min_x - (max_x - min_x) * 0.05\n",
" max_x = max_x + (max_x - min_x) * 0.05\n",
" min_y = min_y - (max_y - min_y) * 0.05\n",
" max_y = max_y + (max_y - min_y) * 0.05\n",
" x_vals = np.linspace(min_x, max_x, 30)\n",
" y_vals = np.linspace(min_y, max_y, 30)\n",
" XX, YY = np.meshgrid(x_vals, y_vals)\n",
" grid_r, grid_c = XX.shape\n",
" ZZ = np.zeros((grid_r, grid_c))\n",
" for i in range(grid_r):\n",
" for j in range(grid_c):\n",
" '''\n",
" Here 'model' is the neural network you previous trained.\n",
" '''\n",
" ZZ[i, j] = pred_fun(model, XX[i, j], YY[i, j])\n",
" plt.contourf(XX, YY, ZZ, 30, cmap = pl.cm.coolwarm, vmin= 0, vmax=1)\n",
" plt.colorbar()\n",
" plt.xlabel(\"x\")\n",
" plt.ylabel(\"y\")\n",
" \n",
"def pred_fun(model,x1, x2):\n",
" '''\n",
" Here 'model' is the neural network you previous trained.\n",
" '''\n",
" xval = np.array([[x1, x2]])\n",
" return model.predict(xval)[0, 0]\n",
"\n",
"plt.figure(figsize = (8,16/3)) \n",
"'''\n",
"Here 'model' is the neural network you previous trained.\n",
"'''\n",
"plot_decision_region(model, x_train, pred_fun)\n",
"plot_data(x_train, y_train)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.7"
}
},
"nbformat": 4,
"nbformat_minor": 2
}