{ "cells": [ { "cell_type": "code", "execution_count": 3, "metadata": { "collapsed": true }, "outputs": [], "source": [ "#!pip install numpy scipy matplotlib ipython scikit-learn mglearn sympy pandas pillow" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[[ 1. 0. 0. 0.]\n", " [ 0. 1. 0. 0.]\n", " [ 0. 0. 1. 0.]\n", " [ 0. 0. 0. 1.]]\n", " (0, 0)\t1.0\n", " (1, 1)\t1.0\n", " (2, 2)\t1.0\n", " (3, 3)\t1.0\n" ] }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYYAAAD8CAYAAABzTgP2AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
AgeLocationName
051NairobiJohn
121NapoliAnna
234LondonPeter
345Buenos AiresLinda
\n", "
" ], "text/plain": [ " Age Location Name\n", "0 51 Nairobi John\n", "1 21 Napoli Anna\n", "2 34 London Peter\n", "3 45 Buenos Aires Linda" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import numpy as np\n", "import matplotlib.pyplot as plt\n", "from scipy import sparse\n", "import pandas as pd\n", "from IPython.display import display\n", "eye = np.eye(4)\n", "print(eye)\n", "sparse_mtx = sparse.csr_matrix(eye)\n", "print(sparse_mtx)\n", "x = np.linspace(-10,10,100)\n", "y = np.sin(x)\n", "plt.plot(x,y,marker='x')\n", "plt.show()\n", "data = {'Name': [\"John\", \"Anna\", \"Peter\", \"Linda\"], 'Location': [\"Nairobi\", \"Napoli\", \"London\", \"Buenos Aires\"], 'Age':[51, 21, 34, 45]}\n", "data_pandas = pd.DataFrame(data)\n", "display(data_pandas)" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXYAAAD8CAYAAABjAo9vAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nxv8HDVbzVHZuK9kAAAAASUVORK5CYII=\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import numpy as np\n", "import matplotlib.pyplot as plt\n", "from scipy import sparse\n", "import pandas as pd\n", "from IPython.display import display\n", "import mglearn\n", "import sklearn\n", "from sklearn.linear_model import LinearRegression\n", "from sklearn.tree import DecisionTreeRegressor\n", "x, y = mglearn.datasets.make_wave(n_samples=100)\n", "line = np.linspace(-3,3,1000,endpoint=False).reshape(-1,1)\n", "reg = DecisionTreeRegressor(min_samples_split=3).fit(x,y)\n", "plt.plot(line, reg.predict(line), label=\"decision tree\")\n", "regline = LinearRegression().fit(x,y)\n", "plt.plot(line, regline.predict(line), label= \"Linear Rgression\")\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": true }, "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": "3.6.3" } }, "nbformat": 4, "nbformat_minor": 2 }