diff --git a/Gaussian-Process-Classifier.ipynb b/Gaussian-Process-Classifier.ipynb new file mode 100644 index 0000000..1df9ff5 --- /dev/null +++ b/Gaussian-Process-Classifier.ipynb @@ -0,0 +1,200 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "slideshow": { + "slide_type": "slide" + } + }, + "outputs": [], + "source": [ + "#Import the libraries\n", + "import numpy as np\n", + "import matplotlib.pyplot as plt\n", + "import pandas as pd\n" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "#DATA PRE-PROCESSING\n", + "\n", + "#import the dataset\n", + "dataset = pd.read_csv('Social_Network_Ads.csv')\n", + "X = dataset.iloc[: , [2 ,3]].values\n", + "y = dataset.iloc[: , 4].values" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "#splitting the dataset into the training set and Test set\n", + "from sklearn.model_selection import train_test_split\n", + "X_train , X_test , y_train , y_test = train_test_split(X , y , test_size=0.25 , random_state = 0)" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [], + "source": [ + "from sklearn.preprocessing import StandardScaler\n", + "sc = StandardScaler()\n", + "X_train = sc.fit_transform(X_train)\n", + "X_test = sc.transform(X_test)\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [], + "source": [ + "#see the link in the sklearn API: https://scikit-learn.org/stable/auto_examples/classification/plot_classifier_comparison.html\n", + "from sklearn.gaussian_process import GaussianProcessClassifier\n", + "classifier = GaussianProcessClassifier(random_state = 0)\n", + "classifier.fit(X_train,y_train)\n", + "y_pred = classifier.predict(X_test)" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [], + "source": [ + "from sklearn.metrics import confusion_matrix\n", + "cm = confusion_matrix(y_test, y_pred)" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "'c' argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with 'x' & 'y'. Please use a 2-D array with a single row if you really want to specify the same RGB or RGBA value for all points.\n", + "'c' argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with 'x' & 'y'. Please use a 2-D array with a single row if you really want to specify the same RGB or RGBA value for all points.\n" + ] + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "from matplotlib.colors import ListedColormap\n", + "X_set, y_set = X_train, y_train\n", + "X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),\n", + " np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))\n", + "plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),\n", + " alpha = 0.75, cmap = ListedColormap(('pink', 'lightgreen')))\n", + "plt.xlim(X1.min(), X1.max())\n", + "plt.ylim(X2.min(), X2.max())\n", + "for i, j in enumerate(np.unique(y_set)):\n", + " plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],\n", + " c = ListedColormap(('red', 'green'))(i), label = j)\n", + "plt.title('Classifier (Training set)')\n", + "plt.xlabel('Age')\n", + "plt.ylabel('Estimated Salary')\n", + "plt.legend()\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "'c' argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with 'x' & 'y'. Please use a 2-D array with a single row if you really want to specify the same RGB or RGBA value for all points.\n", + "'c' argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with 'x' & 'y'. Please use a 2-D array with a single row if you really want to specify the same RGB or RGBA value for all points.\n" + ] + }, + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "\n", + "from matplotlib.colors import ListedColormap\n", + "X_set, y_set = X_test, y_test\n", + "X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),\n", + " np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))\n", + "plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),\n", + " alpha = 0.75, cmap = ListedColormap(('pink', 'lightgreen')))\n", + "plt.xlim(X1.min(), X1.max())\n", + "plt.ylim(X2.min(), X2.max())\n", + "for i, j in enumerate(np.unique(y_set)):\n", + " plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],\n", + " c = ListedColormap(('red', 'green'))(i), label = j)\n", + "plt.title('Classifier (Test set)')\n", + "plt.xlabel('Age')\n", + "plt.ylabel('Estimated Salary')\n", + "plt.legend()\n", + "plt.show()" + ] + }, + { + "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": "3.7.1" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/logistic-regression-classifier.ipynb b/logistic-regression-classifier.ipynb index 9c08554..c50703b 100644 --- a/logistic-regression-classifier.ipynb +++ b/logistic-regression-classifier.ipynb @@ -1,5 +1,12 @@ { "cells": [ + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, { "cell_type": "markdown", "metadata": {}, @@ -11,13 +18,14 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 27, "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "import matplotlib.pyplot as plt\n", - "import pandas as pd" + "import pandas as pd\n", + "from sklearn.model_selection import train_test_split" ] }, { @@ -30,7 +38,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 28, "metadata": {}, "outputs": [], "source": [ @@ -48,20 +56,10 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 29, "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/anaconda3/lib/python3.6/site-packages/sklearn/cross_validation.py:41: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.\n", - " \"This module will be removed in 0.20.\", DeprecationWarning)\n" - ] - } - ], + "outputs": [], "source": [ - "from sklearn.cross_validation import train_test_split\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)" ] }, @@ -74,7 +72,14 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 31, "metadata": {}, "outputs": [], "source": [ @@ -84,6 +89,19 @@ "X_test = sc.transform(X_test)" ] }, + { + "cell_type": "code", + "execution_count": 39, + "metadata": {}, + "outputs": [], + "source": [ + "from sklearn.gaussian_process import GaussianProcessClassifier\n", + "classifier = GaussianProcessClassifier(random_state = 0)\n", + "classifier.fit(X_train,y_train)\n", + "# Predicting the Test set results\n", + "y_pred = classifier.predict(X_test)" + ] + }, { "cell_type": "markdown", "metadata": {}, @@ -93,16 +111,10 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 38, "metadata": {}, "outputs": [], - "source": [ - "from sklearn.linear_model import LogisticRegression\n", - "classifier = LogisticRegression(random_state = 0)\n", - "classifier.fit(X_train,y_train)\n", - "# Predicting the Test set results\n", - "y_pred = classifier.predict(X_test)" - ] + "source": [] }, { "cell_type": "markdown", @@ -113,7 +125,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 40, "metadata": {}, "outputs": [], "source": [ @@ -123,15 +135,15 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 41, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "[[65 3]\n", - " [ 8 24]]\n" + "[[64 4]\n", + " [ 3 29]]\n" ] } ], @@ -150,12 +162,20 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 42, "metadata": {}, "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "'c' argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with 'x' & 'y'. Please use a 2-D array with a single row if you really want to specify the same RGB or RGBA value for all points.\n", + "'c' argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with 'x' & 'y'. Please use a 2-D array with a single row if you really want to specify the same RGB or RGBA value for all points.\n" + ] + }, { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -194,12 +214,20 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 43, "metadata": {}, "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "'c' argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with 'x' & 'y'. Please use a 2-D array with a single row if you really want to specify the same RGB or RGBA value for all points.\n", + "'c' argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with 'x' & 'y'. Please use a 2-D array with a single row if you really want to specify the same RGB or RGBA value for all points.\n" + ] + }, { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -268,7 +296,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.8" + "version": "3.7.4" } }, "nbformat": 4, diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..ae12207 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,6 @@ +tensorflow==1.13.1 +numpy==1.16.2 +pandas==0.24.2 +matplotlib==3.0.3 +Keras==2.2.4 +scikit-learn \ No newline at end of file