model = pd.DataFrame(zip(features, coefficients))
print model
X_train[0,:] # first training observation
lr.predict_proba(X_train[0,:]) # what is the predicted probability?
lr.predict(X_train[0,:]) # what is the predicted class?
X_train[13,:] # 13th training observation
lr.predict_proba(X_train[13,:]) # what is the predicted probability?
lr.predict(X_train[13,:]) # what is the predicted class?
from sklearn.metrics import accuracy_score
from sklearn.metrics import confusion_matrix
y_pred = lr.predict(X_test) # apply the model to the test set
accuracy_score(y_test, y_pred) # calculate the accuracy score
y_pred2 = lr.predict(X_train)
accuracy_score(y_train, y_pred2)
# plot
import sys
sys.path.append("C:/Users/Craig/Documents/GitHub/Python-Machine-Learning")
from functions_module import plot_decision_regions
plot_decision_regions(X_train, y_train, lr)
plt.figure(figsize=(20,15))
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.3,
random_state=0)
from sklearn.ensemble import RandomForestClassifier
forest = RandomForestClassifier(criterion='entropy',
n_estimators=10,
random_state=1,
n_jobs=2)
forest.fit(X_train, y_train)
# Plot decision regions of model
import numpy as np
import matplotlib.pyplot as plt
X_combined = np.vstack((X_train, X_test))
y_combined = np.hstack((y_train, y_test))
import sys
sys.path.append("~/Documents/Practice/Python/Repos/Python-Machine-Learning")
from functions_module import plot_decision_regions
plot_decision_regions(X_combined,
y_combined,
classifier=forest,
test_idx=range(105, 150))
plt.xlabel('petal length')
plt.ylabel('petal width')
plt.legend(loc='upper left')
plt.show()
# train SVM
from sklearn.svm import SVC
svm = SVC(kernel = 'linear', C = 1.0, random_state = 0)
svm.fit(X_train_std, y_train)
# plot decision regions of SVM
import sys
import numpy as np
sys.path.append("~/Documents/Practice/Repos/Python-Machine-Learning")
from functions_module import plot_decision_regions
X_combined_std = np.vstack((X_train_std, X_test_std))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X_combined_std,
y_combined,
classifier = svm,
test_idx = range(105, 150))
# kernel SVM
# create XOR gate sample data
import matplotlib.pyplot as plt
np.random.seed(0)
X_xor = np.random.randn(200, 2)
y_xor = np.logical_xor(X_xor[:, 0] > 0, X_xor[:, 1] > 0)
y_xor = np.where(y_xor, 1, -1)
plt.scatter(X_xor[y_xor == 1, 0],
X_xor[y_xor == 1, 1],
# create tree object
from sklearn.tree import DecisionTreeClassifier
tree = DecisionTreeClassifier(criterion = 'entropy',
max_depth = 3,
random_state = 0)
# fit tree on unscaled training data
tree.fit(X_train, y_train)
X_combined = np.vstack((X_train, X_test))
y_combined = np.hstack((y_train, y_test))
import sys
sys.path.append("C:/Users/Craig/Documents/GitHub/Python-Machine-Learning")
from functions_module import plot_decision_regions
plot_decision_regions(X_combined,
y_combined,
classifier = tree,
test_idx = range(105, 150))
plt.xlabel('petal length [cm]')
plt.ylabel('petal width [cm]')
plt.legend(loc = 'upper left')
plt.show()
# create tree diagram for graphviz
from sklearn.tree import export_graphviz
export_graphviz(tree,
out_file = '~/Documents/Practice/Python/Python-Machine-Learning/tree.dot',
feature_names = ['petal length', 'petal width'])
svm = SVC(kernel='linear', C=1.0, random_state=0)
svm.fit(X_train_std, y_train)
# plot decision regions of SVM
import sys
import numpy as np
sys.path.append("~/Documents/Practice/Repos/Python-Machine-Learning")
from functions_module import plot_decision_regions
X_combined_std = np.vstack((X_train_std, X_test_std))
y_combined = np.hstack((y_train, y_test))
plot_decision_regions(X_combined_std,
y_combined,
classifier=svm,
test_idx=range(105, 150))
# kernel SVM
# create XOR gate sample data
import matplotlib.pyplot as plt
np.random.seed(0)
X_xor = np.random.randn(200, 2)
y_xor = np.logical_xor(X_xor[:, 0] > 0, X_xor[:, 1] > 0)
y_xor = np.where(y_xor, 1, -1)
plt.scatter(X_xor[y_xor == 1, 0],
X_xor[y_xor == 1, 1],
c='b',