Types of Machine Learning
.
.
.
Batch and Online Learning
Batch Learning
Online learning
Instance-Based Versus Model-Based Learning
Instance based
Model-based learning
import os
datapath = os.path.join("datasets", "lifesat", "")
# Download the data
import urllib.request
DOWNLOAD_ROOT = "https://raw.githubusercontent.com/ageron/handson-ml2/master/"
os.makedirs(datapath, exist_ok=True)
for filename in ("oecd_bli_2015.csv", "gdp_per_capita.csv"):
print("Downloading", filename)
url = DOWNLOAD_ROOT + "datasets/lifesat/" + filename
urllib.request.urlretrieve(url, datapath + filename)
def prepare_country_stats(oecd_bli, gdp_per_capita):
oecd_bli = oecd_bli[oecd_bli["INEQUALITY"]=="TOT"]
oecd_bli = oecd_bli.pivot(index="Country", columns="Indicator", values="Value")
gdp_per_capita.rename(columns={"2015": "GDP per capita"}, inplace=True)
gdp_per_capita.set_index("Country", inplace=True)
full_country_stats = pd.merge(left=oecd_bli, right=gdp_per_capita,
left_index=True, right_index=True)
full_country_stats.sort_values(by="GDP per capita", inplace=True)
remove_indices = [0, 1, 6, 8, 33, 34, 35]
keep_indices = list(set(range(36)) - set(remove_indices))
return full_country_stats[["GDP per capita", 'Life satisfaction']].iloc[keep_indices]
# To plot pretty figures directly within Jupyter
%matplotlib inline
import matplotlib as mpl
mpl.rc('axes', labelsize=14)
mpl.rc('xtick', labelsize=12)
mpl.rc('ytick', labelsize=12)
gdp_per_capita.head()
import matplotlib
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import sklearn.linear_model
# Load the data
oecd_bli = pd.read_csv("/work/ch_1/datasets/lifesat/oecd_bli_2015.csv", thousands=',')
# /work/ch_1/datasets/lifesat/oecd_bli_2015.csv
gdp_per_capita = pd.read_csv("/work/ch_1/ch_1_note_s.ipynb",thousands=',',delimiter='\t',
encoding='latin1', na_values="n/a")
# Prepare the data
country_stats = prepare_country_stats(oecd_bli, gdp_per_capita)
X = np.c_[country_stats["GDP per capita"]]
y = np.c_[country_stats["Life satisfaction"]]
# Visualize the data
country_stats.plot(kind='scatter', x="GDP per capita", y='Life satisfaction')
plt.show()
# Select a linear model
model = sklearn.linear_model.LinearRegression()
# Train the model
model.fit(X, y)
# Make a prediction for Cyprus
X_new = [[22587]] # Cyprus' GDP per capita
print(model.predict(X_new)) # outputs [[ 5.96242338]]
filename