Modeling Real Data

Introduction to Linear Modeling in Python

Jason Vestuto

Data Scientist

Scikit-Learn

from sklearn.linear_model import LinearRegression
# Initialize a general model
model = LinearRegression(fit_intercept=True)

# Load and shape the data
x_raw, y_raw = load_data()
x_data = x_raw.reshape(len(y_raw),1)
y_data = y_raw.reshape(len(y_raw),1)

# Fit the model to the data
model_fit = model.fit(x_data, y_data)

# Extract the linear model parameters
intercept = model.intercept_[0]
slope = model.coef_[0,0]

# Use the model to make predictions
future_x = 2100
future_y = model.predict(future_x)

x, y = load_data()
df = pd.DataFrame(dict(times=x_data, distances=y_data))

fig = df.plot('times', 'distances')

model_fit = ols(formula="distances ~ times", data=df).fit()

a0 = model_fit.params['Intercept']
a1 = model_fit.params['times']

e0 = model_fit.bse['Intercept']
e1 = model_fit.bse['times']

intercept = a0
slope = a1
uncertainty_in_intercept = e0
uncertainty_in_slope = e1

Introduction to Linear Modeling in Python