ml-finance-python

python scripts for finance machine learning

git clone https://9o.is/git/ml-finance-python.git

lasso_regression.py

(1988B)

      1 from __future__ import print_function
      2 import matplotlib.pyplot as plt
      3 import numpy as np
      4 import pandas as pd
      5 # Import helper functions
      6 from mlfromscratch.supervised_learning import LassoRegression
      7 from mlfromscratch.utils import k_fold_cross_validation_sets, normalize, mean_squared_error
      8 from mlfromscratch.utils import train_test_split, polynomial_features, Plot
      9 
     10 
     11 def main():
     12 
     13     # Load temperature data
     14     data = pd.read_csv('mlfromscratch/data/TempLinkoping2016.txt', sep="\t")
     15 
     16     time = np.atleast_2d(data["time"].values).T
     17     temp = data["temp"].values
     18 
     19     X = time # fraction of the year [0, 1]
     20     y = temp
     21 
     22     X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)
     23 
     24     poly_degree = 13
     25 
     26     model = LassoRegression(degree=15, 
     27                             reg_factor=0.05,
     28                             learning_rate=0.001,
     29                             n_iterations=4000)
     30     model.fit(X_train, y_train)
     31 
     32     # Training error plot
     33     n = len(model.training_errors)
     34     training, = plt.plot(range(n), model.training_errors, label="Training Error")
     35     plt.legend(handles=[training])
     36     plt.title("Error Plot")
     37     plt.ylabel('Mean Squared Error')
     38     plt.xlabel('Iterations')
     39     plt.show()
     40 
     41     y_pred = model.predict(X_test)
     42     mse = mean_squared_error(y_test, y_pred)
     43     print ("Mean squared error: %s (given by reg. factor: %s)" % (mse, 0.05))
     44 
     45     y_pred_line = model.predict(X)
     46 
     47     # Color map
     48     cmap = plt.get_cmap('viridis')
     49 
     50     # Plot the results
     51     m1 = plt.scatter(366 * X_train, y_train, color=cmap(0.9), s=10)
     52     m2 = plt.scatter(366 * X_test, y_test, color=cmap(0.5), s=10)
     53     plt.plot(366 * X, y_pred_line, color='black', linewidth=2, label="Prediction")
     54     plt.suptitle("Lasso Regression")
     55     plt.title("MSE: %.2f" % mse, fontsize=10)
     56     plt.xlabel('Day')
     57     plt.ylabel('Temperature in Celcius')
     58     plt.legend((m1, m2), ("Training data", "Test data"), loc='lower right')
     59     plt.show()
     60 
     61 if __name__ == "__main__":
     62     main()