arthur/handson-ml3
1
0
Fork 0
mirror of https://github.com/ArthurDanjou/handson-ml3.git synced 2026-01-30 19:47:49 +01:00
Code Issues Packages Projects Releases Wiki Activity

Add fundamentals and training_linear_models notebooks

Browse Source
This commit is contained in:
Aurélien Geron
2016-05-22 16:01:18 +02:00
parent 373535d8e4
commit 240f3d7828
3 changed files with 1743 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files

179
end_to_end_project.ipynb
View File

@@ -27,11 +27,26 @@
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
"collapsed": false
},
"outputs": [],
"source": [
"from __future__ import division, print_function, unicode_literals"
"from __future__ import division, print_function, unicode_literals\n",
"\n",
"%matplotlib inline\n",
"import matplotlib.pyplot as plt\n",
"plt.rcParams['axes.labelsize'] = 14\n",
"plt.rcParams['xtick.labelsize'] = 12\n",
"plt.rcParams['ytick.labelsize'] = 12\n",
"\n",
"PROJECT_ROOT_DIR = \".\"\n",
"CHAPTER_ID = \"end_to_end_project\"\n",
"\n",
"def save_fig(fig_id):\n",
" path = os.path.join(PROJECT_ROOT_DIR, \"images\", CHAPTER_ID, fig_id + \".png\")\n",
" print(\"Saving figure\", fig_id)\n",
" plt.tight_layout()\n",
" plt.savefig(path, format='png', dpi=300)"
]
},
{
@@ -157,7 +172,8 @@
"source": [
"%matplotlib inline\n",
"import matplotlib.pyplot as plt\n",
"housing.hist(bins=50, figsize=(20,15))\n",
"housing.hist(bins=50, figsize=(11,8))\n",
"save_fig(\"attribute_histogram_plots\")\n",
"plt.show()"
]
},
@@ -171,6 +187,7 @@
"source": [
"import numpy as np\n",
"import numpy.random as rnd\n",
"rnd.seed(42) # to make this notebook's output identical at every run\n",
"\n",
"def split_train_test(data, test_ratio):\n",
" shuffled_indices = rnd.permutation(len(data))\n",
@@ -349,7 +366,8 @@
},
"outputs": [],
"source": [
"housing.plot(kind=\"scatter\", x=\"longitude\", y=\"latitude\")"
"housing.plot(kind=\"scatter\", x=\"longitude\", y=\"latitude\")\n",
"save_fig(\"bad_visualization\")"
]
},
{
@@ -360,23 +378,27 @@
},
"outputs": [],
"source": [
"housing.plot(kind=\"scatter\", x=\"longitude\", y=\"latitude\", alpha=0.1)"
"housing.plot(kind=\"scatter\", x=\"longitude\", y=\"latitude\", alpha=0.1)\n",
"save_fig(\"better_visualization\")"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {
"collapsed": false
"collapsed": false,
"scrolled": true
},
"outputs": [],
"source": [
"housing.plot(kind=\"scatter\", x=\"longitude\", y=\"latitude\",\n",
" s=housing['population']/100, label=\"population\",\n",
" c=\"median_house_value\", cmap=plt.get_cmap(\"jet\"),\n",
" colorbar=True, alpha=0.4,\n",
" colorbar=True, alpha=0.4, figsize=(10,7),\n",
")\n",
"plt.legend()"
"plt.legend()\n",
"save_fig(\"housing_prices_scatterplot\")\n",
"plt.show()"
]
},
{
@@ -386,6 +408,36 @@
"collapsed": false
},
"outputs": [],
"source": [
"import matplotlib.image as mpimg\n",
"california_img=mpimg.imread(PROJECT_ROOT_DIR + '/images/end_to_end_project/california.png')\n",
"ax = housing.plot(kind=\"scatter\", x=\"longitude\", y=\"latitude\", figsize=(10,7),\n",
" s=housing['population']/100, label=\"Population\",\n",
" c=\"median_house_value\", cmap=plt.get_cmap(\"jet\"),\n",
" colorbar=False, alpha=0.4,\n",
" )\n",
"plt.imshow(california_img, extent=[-124.55, -113.80, 32.45, 42.05], alpha=0.5)\n",
"plt.ylabel(\"Latitude\", fontsize=14)\n",
"plt.xlabel(\"Longitude\", fontsize=14)\n",
"\n",
"prices = housing[\"median_house_value\"]\n",
"tick_values = np.linspace(prices.min(), prices.max(), 11)\n",
"cbar = plt.colorbar()\n",
"cbar.ax.set_yticklabels([\"$%dk\"%(round(v/1000)) for v in tick_values], fontsize=14)\n",
"cbar.set_label('Median House Value', fontsize=16)\n",
"\n",
"plt.legend(fontsize=16)\n",
"save_fig(\"california_housing_prices\")\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"corr_matrix = housing.corr()\n",
"corr_matrix[\"median_house_value\"].sort_values(ascending=False)"
@@ -393,7 +445,7 @@
},
{
"cell_type": "code",
"execution_count": 27,
"execution_count": 28,
"metadata": {
"collapsed": false
},
@@ -401,12 +453,14 @@
"source": [
"housing.plot(kind=\"scatter\", x=\"median_income\", y=\"median_house_value\",\n",
" alpha=0.3)\n",
"plt.axis([0, 16, 0, 550000])"
"plt.axis([0, 16, 0, 550000])\n",
"save_fig(\"income_vs_house_value_scatterplot\")\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 28,
"execution_count": 29,
"metadata": {
"collapsed": false
},
@@ -415,13 +469,14 @@
"from pandas.tools.plotting import scatter_matrix\n",
"\n",
"attributes = [\"median_house_value\", \"median_income\", \"total_rooms\", \"housing_median_age\"]\n",
"scatter_matrix(housing[attributes], figsize=(12, 8))\n",
"scatter_matrix(housing[attributes], figsize=(11, 8))\n",
"save_fig(\"scatter_matrix_plot\")\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 29,
"execution_count": 30,
"metadata": {
"collapsed": true
},
@@ -434,7 +489,7 @@
},
{
"cell_type": "code",
"execution_count": 30,
"execution_count": 31,
"metadata": {
"collapsed": false
},
@@ -446,7 +501,7 @@
},
{
"cell_type": "code",
"execution_count": 31,
"execution_count": 32,
"metadata": {
"collapsed": false
},
@@ -460,7 +515,7 @@
},
{
"cell_type": "code",
"execution_count": 32,
"execution_count": 33,
"metadata": {
"collapsed": false
},
@@ -478,7 +533,7 @@
},
{
"cell_type": "code",
"execution_count": 33,
"execution_count": 34,
"metadata": {
"collapsed": true
},
@@ -490,7 +545,7 @@
},
{
"cell_type": "code",
"execution_count": 34,
"execution_count": 35,
"metadata": {
"collapsed": false
},
@@ -502,7 +557,7 @@
},
{
"cell_type": "code",
"execution_count": 35,
"execution_count": 36,
"metadata": {
"collapsed": false
},
@@ -513,7 +568,7 @@
},
{
"cell_type": "code",
"execution_count": 36,
"execution_count": 37,
"metadata": {
"collapsed": false
},
@@ -525,7 +580,7 @@
},
{
"cell_type": "code",
"execution_count": 37,
"execution_count": 38,
"metadata": {
"collapsed": false
},
@@ -539,7 +594,7 @@
},
{
"cell_type": "code",
"execution_count": 38,
"execution_count": 39,
"metadata": {
"collapsed": false
},
@@ -557,7 +612,7 @@
},
{
"cell_type": "code",
"execution_count": 39,
"execution_count": 40,
"metadata": {
"collapsed": false
},
@@ -568,7 +623,7 @@
},
{
"cell_type": "code",
"execution_count": 40,
"execution_count": 41,
"metadata": {
"collapsed": false
},
@@ -579,7 +634,7 @@
},
{
"cell_type": "code",
"execution_count": 41,
"execution_count": 42,
"metadata": {
"collapsed": false
},
@@ -590,7 +645,7 @@
},
{
"cell_type": "code",
"execution_count": 42,
"execution_count": 43,
"metadata": {
"collapsed": false
},
@@ -602,7 +657,7 @@
},
{
"cell_type": "code",
"execution_count": 43,
"execution_count": 44,
"metadata": {
"collapsed": false
},
@@ -618,7 +673,7 @@
},
{
"cell_type": "code",
"execution_count": 44,
"execution_count": 45,
"metadata": {
"collapsed": false
},
@@ -629,7 +684,7 @@
},
{
"cell_type": "code",
"execution_count": 45,
"execution_count": 46,
"metadata": {
"collapsed": false
},
@@ -644,7 +699,7 @@
},
{
"cell_type": "code",
"execution_count": 46,
"execution_count": 47,
"metadata": {
"collapsed": false
},
@@ -655,7 +710,7 @@
},
{
"cell_type": "code",
"execution_count": 47,
"execution_count": 48,
"metadata": {
"collapsed": false
},
@@ -669,7 +724,7 @@
},
{
"cell_type": "code",
"execution_count": 48,
"execution_count": 49,
"metadata": {
"collapsed": false
},
@@ -702,7 +757,7 @@
},
{
"cell_type": "code",
"execution_count": 49,
"execution_count": 50,
"metadata": {
"collapsed": false
},
@@ -722,7 +777,7 @@
},
{
"cell_type": "code",
"execution_count": 50,
"execution_count": 51,
"metadata": {
"collapsed": false
},
@@ -761,7 +816,7 @@
},
{
"cell_type": "code",
"execution_count": 51,
"execution_count": 52,
"metadata": {
"collapsed": false
},
@@ -773,7 +828,7 @@
},
{
"cell_type": "code",
"execution_count": 52,
"execution_count": 53,
"metadata": {
"collapsed": false
},
@@ -791,7 +846,7 @@
},
{
"cell_type": "code",
"execution_count": 53,
"execution_count": 54,
"metadata": {
"collapsed": false
},
@@ -805,7 +860,7 @@
},
{
"cell_type": "code",
"execution_count": 54,
"execution_count": 55,
"metadata": {
"collapsed": false
},
@@ -822,7 +877,7 @@
},
{
"cell_type": "code",
"execution_count": 55,
"execution_count": 56,
"metadata": {
"collapsed": false
},
@@ -838,7 +893,7 @@
},
{
"cell_type": "code",
"execution_count": 56,
"execution_count": 57,
"metadata": {
"collapsed": false
},
@@ -852,7 +907,7 @@
},
{
"cell_type": "code",
"execution_count": 57,
"execution_count": 58,
"metadata": {
"collapsed": false
},
@@ -877,7 +932,7 @@
},
{
"cell_type": "code",
"execution_count": 58,
"execution_count": 59,
"metadata": {
"collapsed": false
},
@@ -892,7 +947,7 @@
},
{
"cell_type": "code",
"execution_count": 59,
"execution_count": 60,
"metadata": {
"collapsed": false
},
@@ -908,7 +963,7 @@
},
{
"cell_type": "code",
"execution_count": 60,
"execution_count": 61,
"metadata": {
"collapsed": false
},
@@ -922,7 +977,7 @@
},
{
"cell_type": "code",
"execution_count": 61,
"execution_count": 62,
"metadata": {
"collapsed": false
},
@@ -940,7 +995,7 @@
},
{
"cell_type": "code",
"execution_count": 62,
"execution_count": 63,
"metadata": {
"collapsed": false
},
@@ -956,7 +1011,7 @@
},
{
"cell_type": "code",
"execution_count": 63,
"execution_count": 64,
"metadata": {
"collapsed": false
},
@@ -968,7 +1023,7 @@
},
{
"cell_type": "code",
"execution_count": 64,
"execution_count": 65,
"metadata": {
"collapsed": false
},
@@ -986,7 +1041,7 @@
},
{
"cell_type": "code",
"execution_count": 65,
"execution_count": 66,
"metadata": {
"collapsed": false
},
@@ -1006,7 +1061,7 @@
},
{
"cell_type": "code",
"execution_count": 66,
"execution_count": 67,
"metadata": {
"collapsed": false
},
@@ -1017,7 +1072,7 @@
},
{
"cell_type": "code",
"execution_count": 67,
"execution_count": 68,
"metadata": {
"collapsed": false
},
@@ -1028,7 +1083,7 @@
},
{
"cell_type": "code",
"execution_count": 68,
"execution_count": 69,
"metadata": {
"collapsed": false
},
@@ -1040,7 +1095,7 @@
},
{
"cell_type": "code",
"execution_count": 69,
"execution_count": 70,
"metadata": {
"collapsed": false
},
@@ -1062,7 +1117,7 @@
},
{
"cell_type": "code",
"execution_count": 70,
"execution_count": 71,
"metadata": {
"collapsed": false
},
@@ -1074,7 +1129,7 @@
},
{
"cell_type": "code",
"execution_count": 71,
"execution_count": 72,
"metadata": {
"collapsed": false
},
@@ -1086,7 +1141,7 @@
},
{
"cell_type": "code",
"execution_count": 72,
"execution_count": 73,
"metadata": {
"collapsed": false
},
@@ -1100,7 +1155,7 @@
},
{
"cell_type": "code",
"execution_count": 73,
"execution_count": 74,
"metadata": {
"collapsed": false
},
@@ -1138,7 +1193,7 @@
},
{
"cell_type": "code",
"execution_count": 74,
"execution_count": 75,
"metadata": {
"collapsed": false
},
@@ -1170,7 +1225,7 @@
},
{
"cell_type": "code",
"execution_count": 75,
"execution_count": 76,
"metadata": {
"collapsed": true
},
@@ -1181,7 +1236,7 @@
},
{
"cell_type": "code",
"execution_count": 76,
"execution_count": 77,
"metadata": {
"collapsed": false
},
@@ -1192,7 +1247,7 @@
},
{
"cell_type": "code",
"execution_count": 77,
"execution_count": 78,
"metadata": {
"collapsed": false
},
@@ -1211,7 +1266,7 @@
},
{
"cell_type": "code",
"execution_count": 78,
"execution_count": 79,
"metadata": {
"collapsed": false
},