update on machine learning

doc/src/How2ReadData/test.py

@@ -0,0 +1,21 @@
+import numpy as np
+import matplotlib.pyplot as plt
+from IPython.display import display
+import sklearn
+from sklearn.linear_model import LinearRegression
+from sklearn.tree import DecisionTreeRegressor
+from sklearn.model_selection import train_test_split
+X_train, X_test, y_train, y_test = train_test_split(x, y, random_state=0)
+
+data = np.loadtxt('src/Hudson_Bay.csv', delimiter=',', skiprows=1)
+x = data[:,0]
+y = data[:,1]
+x_train,  y_train = train_test_split(x, y, random_state=0)
+line = np.linspace(1900,1930,1000,endpoint=False).reshape(-1,1)
+reg = DecisionTreeRegressor(min_samples_split=3).fit(x.reshape(-1,1),y.reshape(-1,1))
+plt.plot(line, reg.predict(line), label="decision tree")
+regline = LinearRegression().fit(x.reshape(-1,1),y.reshape(-1,1))
+plt.plot(line, regline.predict(line), label= "Linear Regression")
+plt.plot(x, y, label= "Linear Regression")
+plt.show()
+