In [31]:
import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets, linear_model
from sklearn.metrics import accuracy_score, r2_score
from sklearn.model_selection import train_test_split
In [6]:
iris = datasets.load_iris()
In [7]:
iris
Out[7]:
Petal features:¶
In [88]:
iris_X = iris.data[:, 2:]
iris_y = iris.target
In [89]:
iris_X_train, iris_X_test, iris_y_train, iris_y_test = train_test_split(iris_X, iris_y, test_size=0.2)
In [90]:
logistic = linear_model.LogisticRegression()
In [91]:
logistic.fit(iris_X_train, iris_y_train)
Out[91]:
In [92]:
iris_y_pred = logistic.predict(iris_X_test)
In [93]:
# Print the coefficients
print('Coefficients: ', logistic.coef_)
# Print mean squared error
print("Accuracy: %.2f" % accuracy_score(iris_y_test, iris_y_pred))
# Print explained variance score: 1 is perfect prediction
print('Variance score: %.2f' % r2_score(iris_y_test, iris_y_pred))
In [120]:
x_min, x_max = iris_X[:, 0].min() - .5, iris_X[:, 0].max() + .5
y_min, y_max = iris_X[:, 1].min() - .5, iris_X[:, 1].max() + .5
plt.figure(2, figsize=(12, 9))
plt.clf()
# Plot the training points
plt.scatter(iris_X[:, 0], iris_X[:, 1], c=y, cmap=plt.cm.Set1, edgecolor='k')
plt.xlabel('Petal length')
plt.ylabel('Petal width')
plt.xlim(x_min, x_max)
plt.ylim(y_min, y_max)
plt.xticks(())
plt.yticks(())
Out[120]:
In [106]:
iris_y_pred[iris_y_test == 0]
Out[106]:
In [108]:
iris_y_pred[iris_y_test == 1]
Out[108]:
In [107]:
iris_y_pred[iris_y_test == 2]
Out[107]:
In [ ]:
x_min, x_max = iris_X[:, 0].min() - .5, iris_X[:, 0].max() + .5
y_min, y_max = iris_X[:, 1].min() - .5, iris_X[:, 1].max() + .5
plt.figure(2, figsize=(8, 6))
plt.clf()
# Plot the training points
plt.scatter(iris_X[:, 0], iris_X[:, 1], c=y, cmap=plt.cm.Set1, edgecolor='k')
plt.xlabel('Petal length')
plt.ylabel('Petal width')
plt.xlim(x_min, x_max)
plt.ylim(y_min, y_max)
plt.xticks(())
plt.yticks(())
In [117]:
import numpy as np
import matplotlib.pyplot as plt
from sklearn import linear_model, datasets
# import some data to play with
iris = datasets.load_iris()
X = iris.data[:, 2:] # we only take the first two features.
Y = iris.target
h = .02 # step size in the mesh
logreg = linear_model.LogisticRegression(C=1e5)
# we create an instance of Neighbours Classifier and fit the data.
logreg.fit(X, Y)
# Plot the decision boundary. For that, we will assign a color to each
# point in the mesh [x_min, x_max]x[y_min, y_max].
x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
Z = logreg.predict(np.c_[xx.ravel(), yy.ravel()])
# Put the result into a color plot
Z = Z.reshape(xx.shape)
plt.figure(1, figsize=(12, 9))
plt.pcolormesh(xx, yy, Z, cmap=plt.cm.Paired)
# Plot also the training points
plt.scatter(X[:, 0], X[:, 1], c=Y, edgecolors='k', cmap=plt.cm.Paired)
plt.xlabel('Petal length')
plt.ylabel('Petal width')
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
plt.xticks(())
plt.yticks(())
plt.show()
Sepal features:¶
In [82]:
iris_X = iris.data[:, :2]
iris_y = iris.target
In [83]:
iris_X_train, iris_X_test, iris_y_train, iris_y_test = train_test_split(iris_X, iris_y, test_size=0.2)
In [84]:
logistic.fit(iris_X_train, iris_y_train)
Out[84]:
In [85]:
# Print the coefficients
print('Coefficients: ', logistic.coef_)
# Print mean squared error
print("Accuracy: %.2f" % accuracy_score(iris_y_test, iris_y_pred))
# Print explained variance score: 1 is perfect prediction
print('Variance score: %.2f' % r2_score(iris_y_test, iris_y_pred))
In [118]:
x_min, x_max = iris_X[:, 0].min() - .5, iris_X[:, 0].max() + .5
y_min, y_max = iris_X[:, 1].min() - .5, iris_X[:, 1].max() + .5
plt.figure(2, figsize=(12, 9))
plt.clf()
# Plot the training points
plt.scatter(iris_X[:, 0], iris_X[:, 1], c=y, cmap=plt.cm.Set1, edgecolor='k')
plt.xlabel('Petal length')
plt.ylabel('Petal width')
plt.xlim(x_min, x_max)
plt.ylim(y_min, y_max)
plt.xticks(())
plt.yticks(())
Out[118]:
In [119]:
import numpy as np
import matplotlib.pyplot as plt
from sklearn import linear_model, datasets
# import some data to play with
iris = datasets.load_iris()
X = iris.data[:, :2] # we only take the first two features.
Y = iris.target
h = .02 # step size in the mesh
logreg = linear_model.LogisticRegression(C=1e5)
# we create an instance of Neighbours Classifier and fit the data.
logreg.fit(X, Y)
# Plot the decision boundary. For that, we will assign a color to each
# point in the mesh [x_min, x_max]x[y_min, y_max].
x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
Z = logreg.predict(np.c_[xx.ravel(), yy.ravel()])
# Put the result into a color plot
Z = Z.reshape(xx.shape)
plt.figure(1, figsize=(12, 9))
plt.pcolormesh(xx, yy, Z, cmap=plt.cm.Paired)
# Plot also the training points
plt.scatter(X[:, 0], X[:, 1], c=Y, edgecolors='k', cmap=plt.cm.Paired)
plt.xlabel('Sepal length')
plt.ylabel('Sepal width')
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
plt.xticks(())
plt.yticks(())
plt.show()
In [44]:
X = iris.data
y = iris.target
In [10]:
len(X)
Out[10]:
In [16]:
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
In [17]:
len(X_train)
Out[17]:
In [53]:
logistic.fit(X_train, y_train)
Out[53]:
In [54]:
y_pred = logistic.predict(X_test)
In [32]:
# Print the coefficients
print('Coefficients: ', logistic.coef_)
# Print mean squared error
print("Accuracy: %.2f" % accuracy_score(y_test, y_pred))
# Print explained variance score: 1 is perfect prediction
print('Variance score: %.2f' % r2_score(y_test, y_pred))
In [87]:
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from sklearn import datasets
from sklearn.decomposition import PCA
iris = datasets.load_iris()
# To getter a better understanding of interaction of the dimensions
# plot the first three PCA dimensions
fig = plt.figure(1, figsize=(8, 6))
ax = Axes3D(fig, elev=-150, azim=110)
X_reduced = PCA(n_components=3).fit_transform(iris.data)
ax.scatter(X_reduced[:, 0], X_reduced[:, 1], X_reduced[:, 2], c=y,
cmap=plt.cm.Set1, edgecolor='k', s=40)
ax.set_title("First three PCA directions")
ax.set_xlabel("1st eigenvector")
ax.w_xaxis.set_ticklabels([])
ax.set_ylabel("2nd eigenvector")
ax.w_yaxis.set_ticklabels([])
ax.set_zlabel("3rd eigenvector")
ax.w_zaxis.set_ticklabels([])
plt.show()
