Make the code example 1-1 easier to read, and create a better `prepare_country_stats()` function
Aurélien Geron
parent
c8b7f045ee
commit
94914db82e
|
|
@ -2,10 +2,7 @@
|
|||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**Chapter 1 – The Machine Learning landscape**\n",
|
||||
"\n",
|
||||
|
|
@ -14,20 +11,14 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Setup"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"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:"
|
||||
]
|
||||
|
|
@ -36,9 +27,6 @@
|
|||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true,
|
||||
"slideshow": {
|
||||
"slide_type": "-"
|
||||
}
|
||||
|
|
@ -50,11 +38,10 @@
|
|||
"\n",
|
||||
"# Common imports\n",
|
||||
"import numpy as np\n",
|
||||
"import numpy.random as rnd\n",
|
||||
"import os\n",
|
||||
"\n",
|
||||
"# to make this notebook's output stable across runs\n",
|
||||
"rnd.seed(42)\n",
|
||||
"np.random.seed(42)\n",
|
||||
"\n",
|
||||
"# To plot pretty figures\n",
|
||||
"%matplotlib inline\n",
|
||||
|
|
@ -73,35 +60,173 @@
|
|||
" print(\"Saving figure\", fig_id)\n",
|
||||
" if tight_layout:\n",
|
||||
" plt.tight_layout()\n",
|
||||
" plt.savefig(path, format='png', dpi=300)"
|
||||
" plt.savefig(path, format='png', dpi=300)\n",
|
||||
"\n",
|
||||
"# Ignore useless warnings (see SciPy issue #5998)\n",
|
||||
"import warnings\n",
|
||||
"warnings.filterwarnings(action=\"ignore\", module=\"scipy\", message=\"^internal gelsd\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Load and prepare Life satisfaction data"
|
||||
"# Code example 1-1"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"This function just merges the OECD's life satisfaction data and the IMF's GDP per capita data. It's a bit too long and boring and it's not specific to Machine Learning, which is why I left it out of the book."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def prepare_country_stats(oecd_bli, gdp_per_capita):\n",
|
||||
" oecd_bli = oecd_bli[oecd_bli[\"INEQUALITY\"]==\"TOT\"]\n",
|
||||
" oecd_bli = oecd_bli.pivot(index=\"Country\", columns=\"Indicator\", values=\"Value\")\n",
|
||||
" gdp_per_capita.rename(columns={\"2015\": \"GDP per capita\"}, inplace=True)\n",
|
||||
" gdp_per_capita.set_index(\"Country\", inplace=True)\n",
|
||||
" full_country_stats = pd.merge(left=oecd_bli, right=gdp_per_capita,\n",
|
||||
" left_index=True, right_index=True)\n",
|
||||
" full_country_stats.sort_values(by=\"GDP per capita\", inplace=True)\n",
|
||||
" remove_indices = [0, 1, 6, 8, 33, 34, 35]\n",
|
||||
" keep_indices = list(set(range(36)) - set(remove_indices))\n",
|
||||
" return full_country_stats[[\"GDP per capita\", 'Life satisfaction']].iloc[keep_indices]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The code in the book expects the data files to be located in the current directory. I just tweaked it here to fetch the files in datasets/lifesat."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"datapath = os.path.join(\"datasets\", \"lifesat\", \"\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Code example\n",
|
||||
"import matplotlib\n",
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"import numpy as np\n",
|
||||
"import pandas as pd\n",
|
||||
"import sklearn.linear_model\n",
|
||||
"\n",
|
||||
"# Download CSV from http://stats.oecd.org/index.aspx?DataSetCode=BLI\n",
|
||||
"datapath = \"datasets/lifesat/\"\n",
|
||||
"# Load the data\n",
|
||||
"oecd_bli = pd.read_csv(datapath + \"oecd_bli_2015.csv\", thousands=',')\n",
|
||||
"gdp_per_capita = pd.read_csv(datapath + \"gdp_per_capita.csv\",thousands=',',delimiter='\\t',\n",
|
||||
" encoding='latin1', na_values=\"n/a\")\n",
|
||||
"\n",
|
||||
"oecd_bli = pd.read_csv(datapath+\"oecd_bli_2015.csv\", thousands=',')\n",
|
||||
"# Prepare the data\n",
|
||||
"country_stats = prepare_country_stats(oecd_bli, gdp_per_capita)\n",
|
||||
"X = np.c_[country_stats[\"GDP per capita\"]]\n",
|
||||
"y = np.c_[country_stats[\"Life satisfaction\"]]\n",
|
||||
"\n",
|
||||
"# Visualize the data\n",
|
||||
"country_stats.plot(kind='scatter', x=\"GDP per capita\", y='Life satisfaction')\n",
|
||||
"plt.show()\n",
|
||||
"\n",
|
||||
"# Select a linear model\n",
|
||||
"model = sklearn.linear_model.LinearRegression()\n",
|
||||
"\n",
|
||||
"# Train the model\n",
|
||||
"model.fit(X, y)\n",
|
||||
"\n",
|
||||
"# Make a prediction for Cyprus\n",
|
||||
"X_new = [[22587]] # Cyprus' GDP per capita\n",
|
||||
"print(model.predict(X_new)) # outputs [[ 5.96242338]]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Note: you can ignore the rest of this notebook, it just generates many of the figures in chapter 1."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Load and prepare Life satisfaction data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"If you want, you can get fresh data from the OECD's website.\n",
|
||||
"Download the CSV from http://stats.oecd.org/index.aspx?DataSetCode=BLI\n",
|
||||
"and save it to `datasets/lifesat/`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"oecd_bli = pd.read_csv(datapath + \"oecd_bli_2015.csv\", thousands=',')\n",
|
||||
"oecd_bli = oecd_bli[oecd_bli[\"INEQUALITY\"]==\"TOT\"]\n",
|
||||
"oecd_bli = oecd_bli.pivot(index=\"Country\", columns=\"Indicator\", values=\"Value\")\n",
|
||||
"oecd_bli.head(2)"
|
||||
|
|
@ -109,12 +234,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"oecd_bli[\"Life satisfaction\"].head()"
|
||||
|
|
@ -122,25 +243,24 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Load and prepare GDP per capita data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Just like above, you can update the GDP per capita data if you want. Just download data from http://goo.gl/j1MSKe (=> imf.org) and save it to `datasets/lifesat/`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Download data from http://goo.gl/j1MSKe (=> imf.org)\n",
|
||||
"gdp_per_capita = pd.read_csv(datapath+\"gdp_per_capita.csv\", thousands=',', delimiter='\\t',\n",
|
||||
" encoding='latin1', na_values=\"n/a\")\n",
|
||||
"gdp_per_capita.rename(columns={\"2015\": \"GDP per capita\"}, inplace=True)\n",
|
||||
|
|
@ -150,12 +270,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"full_country_stats = pd.merge(left=oecd_bli, right=gdp_per_capita, left_index=True, right_index=True)\n",
|
||||
|
|
@ -165,12 +281,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"full_country_stats[[\"GDP per capita\", 'Life satisfaction']].loc[\"United States\"]"
|
||||
|
|
@ -178,12 +290,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"remove_indices = [0, 1, 6, 8, 33, 34, 35]\n",
|
||||
|
|
@ -195,12 +303,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"sample_data.plot(kind='scatter', x=\"GDP per capita\", y='Life satisfaction', figsize=(5,3))\n",
|
||||
|
|
@ -224,25 +328,17 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"sample_data.to_csv(\"life_satisfaction_vs_gdp_per_capita.csv\")"
|
||||
"sample_data.to_csv(os.path.join(\"datasets\", \"lifesat\", \"lifesat.csv\"))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 13,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"sample_data.loc[list(position_text.keys())]"
|
||||
|
|
@ -250,12 +346,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
|
|
@ -278,12 +370,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn import linear_model\n",
|
||||
|
|
@ -297,12 +385,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 16,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"sample_data.plot(kind='scatter', x=\"GDP per capita\", y='Life satisfaction', figsize=(5,3))\n",
|
||||
|
|
@ -317,12 +401,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 17,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"cyprus_gdp_per_capita = gdp_per_capita.loc[\"Cyprus\"][\"GDP per capita\"]\n",
|
||||
|
|
@ -333,12 +413,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 18,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"sample_data.plot(kind='scatter', x=\"GDP per capita\", y='Life satisfaction', figsize=(5,3), s=1)\n",
|
||||
|
|
@ -356,12 +432,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 19,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"sample_data[7:10]"
|
||||
|
|
@ -369,12 +441,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 20,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"(5.1+5.7+6.5)/3"
|
||||
|
|
@ -382,28 +450,29 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 21,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"backup = oecd_bli, gdp_per_capita\n",
|
||||
"\n",
|
||||
"def prepare_country_stats(oecd_bli, gdp_per_capita):\n",
|
||||
" return sample_data"
|
||||
" oecd_bli = oecd_bli[oecd_bli[\"INEQUALITY\"]==\"TOT\"]\n",
|
||||
" oecd_bli = oecd_bli.pivot(index=\"Country\", columns=\"Indicator\", values=\"Value\")\n",
|
||||
" gdp_per_capita.rename(columns={\"2015\": \"GDP per capita\"}, inplace=True)\n",
|
||||
" gdp_per_capita.set_index(\"Country\", inplace=True)\n",
|
||||
" full_country_stats = pd.merge(left=oecd_bli, right=gdp_per_capita,\n",
|
||||
" left_index=True, right_index=True)\n",
|
||||
" full_country_stats.sort_values(by=\"GDP per capita\", inplace=True)\n",
|
||||
" remove_indices = [0, 1, 6, 8, 33, 34, 35]\n",
|
||||
" keep_indices = list(set(range(36)) - set(remove_indices))\n",
|
||||
" return full_country_stats[[\"GDP per capita\", 'Life satisfaction']].iloc[keep_indices]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 19,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 22,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Code example\n",
|
||||
|
|
@ -440,12 +509,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 20,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 23,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"oecd_bli, gdp_per_capita = backup"
|
||||
|
|
@ -453,12 +518,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 21,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 24,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"missing_data"
|
||||
|
|
@ -466,12 +527,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 22,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 25,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"position_text2 = {\n",
|
||||
|
|
@ -487,12 +544,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 23,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 26,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"sample_data.plot(kind='scatter', x=\"GDP per capita\", y='Life satisfaction', figsize=(8,3))\n",
|
||||
|
|
@ -522,12 +575,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 24,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 27,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"full_country_stats.plot(kind='scatter', x=\"GDP per capita\", y='Life satisfaction', figsize=(8,3))\n",
|
||||
|
|
@ -550,12 +599,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 25,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 28,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"full_country_stats.loc[[c for c in full_country_stats.index if \"W\" in c.upper()]][\"Life satisfaction\"]"
|
||||
|
|
@ -563,12 +608,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 26,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 29,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"gdp_per_capita.loc[[c for c in gdp_per_capita.index if \"W\" in c.upper()]].head()"
|
||||
|
|
@ -576,12 +617,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 27,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 30,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"plt.figure(figsize=(8,3))\n",
|
||||
|
|
@ -611,12 +648,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 28,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 31,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"backup = oecd_bli, gdp_per_capita\n",
|
||||
|
|
@ -627,12 +660,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 29,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 32,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Replace this linear model:\n",
|
||||
|
|
@ -641,12 +670,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 30,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 33,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# with this k-neighbors regression model:\n",
|
||||
|
|
@ -655,12 +680,8 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 31,
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"execution_count": 34,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"X = np.c_[country_stats[\"GDP per capita\"]]\n",
|
||||
|
|
@ -677,11 +698,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"deletable": true,
|
||||
"editable": true
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
|
|
@ -702,7 +719,7 @@
|
|||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.5.3"
|
||||
"version": "3.6.3"
|
||||
},
|
||||
"nav_menu": {},
|
||||
"toc": {
|
||||
|
|
@ -723,5 +740,5 @@
|
|||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 0
|
||||
"nbformat_minor": 1
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in New Issue