from sklearn.linear_model import LinearRegression
model = LinearRegression()

import pandas as pd
dataset = pd.DataFrame([
    [1, 2, 3],
    [4, 5, 6],
    [7, 8, 9],
], columns=['x1', 'x2', 'y'])
dataset

X = dataset[['x1', 'x2']].values
X

y = dataset['y'].values
y

model.fit(X, y)

model.predict([[8, 9]])

model.predict([
    [0, 1],
    [8, 9],
])

# Save using pickle
from pickle import dump
dump(model, open('dummy-model.pkl', 'wb'))

# Save using joblib which is another option
import subprocess
subprocess.call('pip install joblib'.split())
from joblib import dump
dump(model, '/tmp/dummy-model.joblib')

from pickle import load
model = load(open('dummy-model.pkl', 'rb'))
model

# Load using joblib which is another option
# import subprocess
# subprocess.call('pip install joblib'.split())
from joblib import load
model = load('/tmp/dummy-model.joblib')
model

import pandas as pd
t = pd.read_csv('example-dataset.csv')
t

X1 = t[[
    'Tree Count Within 100 Meters',
    'Sum of Distances from Trees Within 100 Meters',
    'Average Risk of Trees Within 100 Meters']].values
X1

X2 = t[[
    'Tree Count Within 100 Meters',
    'Average Risk of Trees Within 100 Meters']].values
X2

y = t['Graduation Rate']
y

from sklearn.model_selection import cross_val_score
models = []
scores = []

def train(model, X):
    model.fit(X, y)
    models.append(model)
    score = cross_val_score(
        model, X, y, cv=3,
        scoring='neg_mean_absolute_error',
    ).mean()
    scores.append(score)
    return score

from sklearn.linear_model import LinearRegression
train(LinearRegression(), X1)

train(LinearRegression(), X2)

from sklearn.linear_model import BayesianRidge
train(BayesianRidge(), X1)

train(BayesianRidge(), X2)

from sklearn.svm import SVR
train(SVR(gamma='scale'), X1)

from sklearn.svm import SVR
train(SVR(gamma='scale'), X2)

import numpy as np
best_index = np.argmax(scores)
best_index

best_model = models[best_index]
best_model

import pickle
pickle.dump(best_model, open('/tmp/model.pkl', 'wb'))