Modin Scikit Learn Example

%matplotlib inline

import numpy as np
import modin.pandas as pd
import matplotlib.pyplot as plt
import sklearn

data = pd.read_csv("data/boston_housing.csv")

data.head()

features = data.drop("PRICE", axis=1)
labels = data["PRICE"]

type(features)

from sklearn.linear_model import LinearRegression

lm = LinearRegression()
lm.fit(features, labels)

plt.scatter(data["RM"], labels)
plt.xlabel("Average number of rooms per dwelling")
plt.ylabel("Housing Price")
plt.title("Relationship between Rooms and Price")
plt.show()

predicted_prices = lm.predict(features)

plt.scatter(labels, predicted_prices)
plt.xlabel("Prices")
plt.ylabel("Predicted Prices")
plt.title("Prices versus Predicted Prices")
plt.show()

training_error = \
    (labels - predicted_prices).apply(lambda x: x ** 2).mean()

training_error

# Citation: http://bigdata-madesimple.com/how-to-run-linear-regression-in-python-scikit-learn/