In [1]:
import warnings
warnings.filterwarnings('ignore')
In [2]:
%matplotlib inline
%pylab inline
In [3]:
import pandas as pd
print(pd.__version__)
In [4]:
df = pd.read_csv('./insurance-customers-300.csv', sep=';')
In [5]:
y=df['group']
In [6]:
df.drop('group', axis='columns', inplace=True)
In [7]:
X = df.as_matrix()
In [8]:
df.describe()
Out[8]:
In [9]:
# ignore this, it is just technical code
# should come from a lib, consider it to appear magically
# http://scikit-learn.org/stable/auto_examples/neighbors/plot_classification.html
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
cmap_print = ListedColormap(['#AA8888', '#004000', '#FFFFDD'])
cmap_bold = ListedColormap(['#AA4444', '#006000', '#AAAA00'])
cmap_light = ListedColormap(['#FFAAAA', '#AAFFAA', '#FFFFDD'])
font_size=25
def meshGrid(x_data, y_data):
h = 1 # step size in the mesh
x_min, x_max = x_data.min() - 1, x_data.max() + 1
y_min, y_max = y_data.min() - 1, y_data.max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
np.arange(y_min, y_max, h))
return (xx,yy)
def plotPrediction(clf, x_data, y_data, x_label, y_label, colors, title="", mesh=True, fname=None, print=False):
xx,yy = meshGrid(x_data, y_data)
plt.figure(figsize=(20,10))
if clf and mesh:
Z = clf.predict(np.c_[yy.ravel(), xx.ravel()])
# Put the result into a color plot
Z = Z.reshape(xx.shape)
plt.pcolormesh(xx, yy, Z, cmap=cmap_light)
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
if print:
plt.scatter(x_data, y_data, c=colors, cmap=cmap_print, s=200, marker='o', edgecolors='k')
else:
plt.scatter(x_data, y_data, c=colors, cmap=cmap_bold, s=80, marker='o', edgecolors='k')
plt.xlabel(x_label, fontsize=font_size)
plt.ylabel(y_label, fontsize=font_size)
plt.title(title, fontsize=font_size)
if fname:
plt.savefig(fname)
In [10]:
from sklearn.model_selection import train_test_split
In [11]:
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=42, stratify=y)
In [12]:
X_train.shape, y_train.shape, X_test.shape, y_test.shape
Out[12]:
In [13]:
X_train_kmh_age = X_train[:, :2]
X_test_kmh_age = X_test[:, :2]
X_train_2_dim = X_train_kmh_age
X_test_2_dim = X_test_kmh_age
In [55]:
from sklearn import neighbors
clf = neighbors.KNeighborsClassifier(1)
%time clf.fit(X_train_2_dim, y_train)
Out[55]:
In [56]:
plotPrediction(clf, X_train_2_dim[:, 1], X_train_2_dim[:, 0],
'Age', 'Max Speed', y_train,
title="Train Data Max Speed vs Age with Classification")
In [57]:
clf.score(X_train_2_dim, y_train)
Out[57]:
In [58]:
plotPrediction(clf, X_test_2_dim[:, 1], X_test_2_dim[:, 0],
'Age', 'Max Speed', y_test,
title="Test Data Max Speed vs Age with Prediction",
fname='knn-1.png')
In [59]:
clf.score(X_test_2_dim, y_test)
Out[59]:
Probably still better than our manual result, but this is clearly overfitting
In [26]:
clf = neighbors.KNeighborsClassifier(13)
%time clf.fit(X_train_2_dim, y_train)
Out[26]:
In [27]:
plotPrediction(clf, X_train_2_dim[:, 1], X_train_2_dim[:, 0],
'Age', 'Max Speed', y_train,
title="Train Data Max Speed vs Age with Classification")
In [28]:
clf.score(X_train_2_dim, y_train)
Out[28]:
In [29]:
plotPrediction(clf, X_test_2_dim[:, 1], X_test_2_dim[:, 0],
'Age', 'Max Speed', y_test,
title="Test Data Max Speed vs Age with Prediction",
fname='knn-13.png')
In [23]:
clf.score(X_test_2_dim, y_test)
Out[23]:
In [24]:
clf = neighbors.KNeighborsClassifier(13)
%time clf.fit(X_train, y_train)
Out[24]:
In [25]:
prediction = clf.predict(X)
y_pred = prediction
y_pred
Out[25]:
In [26]:
y_true = np.array(y)
y_true
Out[26]:
In [27]:
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_true, y_pred)
cm
Out[27]:
In [28]:
# 0: red
# 1: green
# 2: yellow
import seaborn as sns
sns.heatmap(cm, annot=True, cmap="YlGnBu")
figure = plt.gcf()
figure.set_size_inches(10, 10)
ax = figure.add_subplot(111)
ax.set_xlabel('Prediction')
ax.set_ylabel('Ground Truth')
Out[28]:
In [ ]: