def test_pairplot_iris():
data = data_df_from_bunch(load_iris())
axes = pairplot(data, target_col='target')
# the diagonal axes are duplicated
# so we can have sharex / sharey
assert axes.shape == (4, 4)
assert len(plt.gcf().get_axes()) == 4 * 4 + 4
def test_plot_classification_continuous():
data = fetch_openml('MiceProtein')
df = data_df_from_bunch(data)
# only univariate plots
figures = plot_classification_continuous(df,
target_col='target',
plot_pairwise=False)
assert len(figures) == 1
# top 10 axes
assert len(figures[0].get_axes()) == 10
# six is the minimum number of features for histograms
# (last column is target)
figures = plot_classification_continuous(df.iloc[:, -7:],
target_col='target',
plot_pairwise=False)
assert len(figures) == 1
assert len(figures[0].get_axes()) == 6
# for 5 features, do full pairplot
figures = plot_classification_continuous(df.iloc[:, -6:],
target_col='target',
plot_pairwise=False)
assert len(figures) == 1
# diagonal has twin axes
assert len(figures[0].get_axes()) == 5 * 5 + 5
# also do pairwise plots
figures = plot_classification_continuous(df,
target_col='target',
random_state=42)
# univariate, pairwise, pca, lda
assert len(figures) == 4
# univariate
axes = figures[0].get_axes()
assert len(axes) == 10
# known result
assert axes[0].get_xlabel() == "SOD1_N"
# bar plot never has ylabel
assert axes[0].get_ylabel() == ""
# pairwise
axes = figures[1].get_axes()
assert len(axes) == 4
# known result
assert axes[0].get_xlabel() == "SOD1_N"
assert axes[0].get_ylabel() == 'S6_N'
# PCA
axes = figures[2].get_axes()
assert len(axes) == 4
# known result
assert axes[0].get_xlabel() == "PCA 1"
assert axes[0].get_ylabel() == 'PCA 5'
# LDA
axes = figures[3].get_axes()
assert len(axes) == 4
# known result
assert axes[0].get_xlabel() == "LDA 0"
assert axes[0].get_ylabel() == 'LDA 1'
def test_data_df_from_bunch():
data_bunch = fetch_openml('MiceProtein')
data = data_df_from_bunch(data_bunch)
assert len(data) == len(data_bunch.data)
assert all(data.target.unique() == [
'c-CS-m', 'c-SC-m', 'c-CS-s', 'c-SC-s', 't-CS-m', 't-SC-m', 't-CS-s',
't-SC-s'
])
def test_regression_boston():
boston = load_boston()
data = data_df_from_bunch(boston)
er = SimpleRegressor()
er.fit(data, target_col='target')
# test nupmy array
er = SimpleRegressor()
er.fit(boston.data, boston.target)
def test_digits_type_hints():
data_bunch = load_digits()
try:
feature_names = data_bunch.feature_names
except AttributeError:
feature_names = ['x%d' % i for i in range(data_bunch.data.shape[1])]
data = data_df_from_bunch(data_bunch)
data_clean = clean(data, type_hints={
feature: 'continuous' for feature in feature_names})
assert data_clean.shape[1] == 65
def test_plot_target_low_card_int():
data = load_digits()
df = data_df_from_bunch(data)
plot(df[::10], target_col='target')
def test_digits_type_hints():
data = data_df_from_bunch(load_digits())
data_clean = clean(
data, type_hints={"x{}".format(i): 'continuous'
for i in range(64)})
assert data_clean.shape[1] == 65
def test_pairplot_iris():
data = data_df_from_bunch(load_iris())
pairplot(data, target_col='target')
""" Wine Classification Dataset Visualization ========================================== """ import matplotlib.pyplot as plt from sklearn.datasets import load_wine from dabl import plot_supervised from dabl.utils import data_df_from_bunch wine_bunch = load_wine() wine_df = data_df_from_bunch(wine_bunch) plot_supervised(wine_df, 'target') plt.show()
# print data(feature)shape
wine.data.shape
# print the wine data features (top 5 records)
print (wine.data[0:5])
print (wine.target)
#Count number of observation in each class
for i in set(wine.target):
print('Class', i, ' -> ', list(wine.target).count(i))
explore()
# Import Gaussian Naive Bayes model
from sklearn.naive_bayes import GaussianNB as GNB
# Train the model using the training sets
# and Predict the response for test dataset
y_pred = GNB().fit(X_train, y_train).predict(X_test)
# Import scikit-learn metrics module for accuracy calculation
from sklearn import metrics
# Model Accuracy, how often is the classifier correct?
print(f"Accuracy: {100*metrics.accuracy_score(y_test, y_pred):.3f}%")
import matplotlib.pyplot as plt
from dabl import plot
from dabl.utils import data_df_from_bunch
plot(data_df_from_bunch(wine), 'target')
plt.show()
