arthur/handson-ml3
1
0
Fork 0
mirror of https://github.com/ArthurDanjou/handson-ml3.git synced 2026-01-30 11:37:49 +01:00
Code Issues Packages Projects Releases Wiki Activity

Upgrade notebooks to TensorFlow 1.0.0

Browse Source
This commit is contained in:
Aurélien Geron
2017-02-17 11:51:26 +01:00
parent 146fde1127
commit d8176ec2cb
43 changed files with 3615 additions and 7542 deletions
Download Patch File Download Diff File Expand all files Collapse all files

394
02_end_to_end_machine_learning_project.ipynb
View File

@@ -2,7 +2,10 @@
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"**Chapter 2 – End-to-end Machine Learning project**\n",
"\n",
@@ -13,14 +16,20 @@
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"# Setup"
]
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"First, let's make sure this notebook works well in both python 2 and 3, import a few common modules, ensure MatplotLib plots figures inline and prepare a function to save the figures:"
]
@@ -29,7 +38,9 @@
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -66,7 +77,10 @@
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"# Get the data"
]
@@ -75,7 +89,9 @@
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
"collapsed": true,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -86,7 +102,9 @@
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -111,7 +129,9 @@
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -122,7 +142,9 @@
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": true
"collapsed": true,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -137,7 +159,9 @@
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -149,7 +173,9 @@
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -160,7 +186,9 @@
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -171,7 +199,9 @@
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -182,7 +212,9 @@
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -197,7 +229,9 @@
"cell_type": "code",
"execution_count": 11,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -217,7 +251,9 @@
"cell_type": "code",
"execution_count": 12,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -229,7 +265,9 @@
"cell_type": "code",
"execution_count": 13,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -248,7 +286,9 @@
"cell_type": "code",
"execution_count": 14,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -261,7 +301,9 @@
"cell_type": "code",
"execution_count": 15,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -275,7 +317,9 @@
"cell_type": "code",
"execution_count": 16,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -286,7 +330,9 @@
"cell_type": "code",
"execution_count": 17,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -299,7 +345,9 @@
"cell_type": "code",
"execution_count": 18,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -315,7 +363,9 @@
"cell_type": "code",
"execution_count": 19,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -337,7 +387,9 @@
"cell_type": "code",
"execution_count": 20,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -348,7 +400,9 @@
"cell_type": "code",
"execution_count": 21,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -358,7 +412,10 @@
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"# Discover and visualize the data to gain insights"
]
@@ -367,7 +424,9 @@
"cell_type": "code",
"execution_count": 22,
"metadata": {
"collapsed": true
"collapsed": true,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -378,7 +437,9 @@
"cell_type": "code",
"execution_count": 23,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -390,7 +451,9 @@
"cell_type": "code",
"execution_count": 24,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -403,6 +466,8 @@
"execution_count": 25,
"metadata": {
"collapsed": false,
"deletable": true,
"editable": true,
"scrolled": true
},
"outputs": [],
@@ -421,7 +486,9 @@
"cell_type": "code",
"execution_count": 26,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -451,7 +518,9 @@
"cell_type": "code",
"execution_count": 27,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -463,7 +532,9 @@
"cell_type": "code",
"execution_count": 28,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -478,7 +549,9 @@
"cell_type": "code",
"execution_count": 29,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -494,7 +567,9 @@
"cell_type": "code",
"execution_count": 30,
"metadata": {
"collapsed": true
"collapsed": true,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -507,7 +582,9 @@
"cell_type": "code",
"execution_count": 31,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -519,7 +596,9 @@
"cell_type": "code",
"execution_count": 32,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -533,7 +612,9 @@
"cell_type": "code",
"execution_count": 33,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -542,7 +623,10 @@
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"# Prepare the data for Machine Learning algorithms"
]
@@ -551,7 +635,9 @@
"cell_type": "code",
"execution_count": 34,
"metadata": {
"collapsed": true
"collapsed": true,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -563,7 +649,9 @@
"cell_type": "code",
"execution_count": 35,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -575,7 +663,9 @@
"cell_type": "code",
"execution_count": 36,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -586,7 +676,9 @@
"cell_type": "code",
"execution_count": 37,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -598,7 +690,9 @@
"cell_type": "code",
"execution_count": 38,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -612,7 +706,9 @@
"cell_type": "code",
"execution_count": 39,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -630,7 +726,9 @@
"cell_type": "code",
"execution_count": 40,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -641,7 +739,9 @@
"cell_type": "code",
"execution_count": 41,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -652,7 +752,9 @@
"cell_type": "code",
"execution_count": 42,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -663,7 +765,9 @@
"cell_type": "code",
"execution_count": 43,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -675,7 +779,9 @@
"cell_type": "code",
"execution_count": 44,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -691,7 +797,9 @@
"cell_type": "code",
"execution_count": 45,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -702,7 +810,9 @@
"cell_type": "code",
"execution_count": 46,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -717,7 +827,9 @@
"cell_type": "code",
"execution_count": 47,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -728,7 +840,9 @@
"cell_type": "code",
"execution_count": 48,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -742,7 +856,9 @@
"cell_type": "code",
"execution_count": 49,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -775,7 +891,9 @@
"cell_type": "code",
"execution_count": 50,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -795,7 +913,9 @@
"cell_type": "code",
"execution_count": 51,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -834,7 +954,9 @@
"cell_type": "code",
"execution_count": 52,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -846,7 +968,9 @@
"cell_type": "code",
"execution_count": 53,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -855,7 +979,10 @@
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"# Prepare the data for Machine Learning algorithms"
]
@@ -864,7 +991,9 @@
"cell_type": "code",
"execution_count": 54,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -878,7 +1007,9 @@
"cell_type": "code",
"execution_count": 55,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -895,7 +1026,9 @@
"cell_type": "code",
"execution_count": 56,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -911,7 +1044,9 @@
"cell_type": "code",
"execution_count": 57,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -925,7 +1060,9 @@
"cell_type": "code",
"execution_count": 58,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -941,7 +1078,10 @@
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"# Fine-tune your model"
]
@@ -950,7 +1090,9 @@
"cell_type": "code",
"execution_count": 59,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -965,7 +1107,9 @@
"cell_type": "code",
"execution_count": 60,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -981,7 +1125,9 @@
"cell_type": "code",
"execution_count": 61,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -995,7 +1141,9 @@
"cell_type": "code",
"execution_count": 62,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -1013,7 +1161,9 @@
"cell_type": "code",
"execution_count": 63,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -1029,7 +1179,9 @@
"cell_type": "code",
"execution_count": 64,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -1041,7 +1193,9 @@
"cell_type": "code",
"execution_count": 65,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -1059,7 +1213,9 @@
"cell_type": "code",
"execution_count": 66,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -1079,7 +1235,9 @@
"cell_type": "code",
"execution_count": 67,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -1090,7 +1248,9 @@
"cell_type": "code",
"execution_count": 68,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -1101,7 +1261,9 @@
"cell_type": "code",
"execution_count": 69,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -1114,7 +1276,9 @@
"cell_type": "code",
"execution_count": 70,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -1125,7 +1289,9 @@
"cell_type": "code",
"execution_count": 71,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -1147,7 +1313,9 @@
"cell_type": "code",
"execution_count": 72,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -1160,7 +1328,9 @@
"cell_type": "code",
"execution_count": 73,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -1172,7 +1342,9 @@
"cell_type": "code",
"execution_count": 74,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -1186,7 +1358,9 @@
"cell_type": "code",
"execution_count": 75,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -1205,14 +1379,20 @@
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"# Extra material"
]
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"## Label Binarizer hack\n",
"`LabelBinarizer`'s `fit_transform()` method only accepts one parameter `y` (because it was meant for labels, not predictors), so it does not work in a pipeline where the final estimator is a supervised estimator because in this case its `fit()` method takes two parameters `X` and `y`.\n",
@@ -1224,7 +1404,9 @@
"cell_type": "code",
"execution_count": 76,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -1247,7 +1429,10 @@
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"## Model persistence using joblib"
]
@@ -1256,7 +1441,9 @@
"cell_type": "code",
"execution_count": 77,
"metadata": {
"collapsed": true
"collapsed": true,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -1267,7 +1454,9 @@
"cell_type": "code",
"execution_count": 78,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -1278,7 +1467,9 @@
"cell_type": "code",
"execution_count": 79,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -1288,7 +1479,10 @@
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"## Example SciPy distributions for `RandomizedSearchCV`"
]
@@ -1297,7 +1491,9 @@
"cell_type": "code",
"execution_count": 80,
"metadata": {
"collapsed": false
"collapsed": false,
"deletable": true,
"editable": true
},
"outputs": [],
"source": [
@@ -1312,14 +1508,20 @@
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"# Exercise solutions"
]
},
{
"cell_type": "markdown",
"metadata": {},
"metadata": {
"deletable": true,
"editable": true
},
"source": [
"**Coming soon**"
]
@@ -1328,7 +1530,9 @@
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
"collapsed": true,
"deletable": true,
"editable": true
},
"outputs": [],
"source": []
@@ -1350,7 +1554,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.5.2"
"version": "3.5.2+"
},
"nav_menu": {
"height": "279px",