def showParallelCoordinates():
# Load the classification data set
data = load_data('occupancy')
# Specify the features of interest and the classes of the target
features = ["temperature", "relative humidity", "light", "C02", "humidity"]
classes = ['unoccupied', 'occupied']
# Extract the numpy arrays from the data frame
X = data[features].as_matrix()
y = data.occupancy.as_matrix()
# Instantiate the visualizer
visualizer = ParallelCoordinates(classes=classes, features=features)
visualizer.fit(X, y) # Fit the data to the visualizer
visualizer.transform(X) # Transform the data
visualizer.poof() # Draw/show/poof the data
# Instantiate the visualizer
visualizer = ParallelCoordinates(
classes=classes,
features=features,
normalize='standard',
sample=0.1,
)
visualizer.fit(X, y) # Fit the data to the visualizer
visualizer.transform(X) # Transform the data
visualizer.poof() # Draw/show/poof the data
def showDirectDataVisualization():
# Load the classification data set
data = load_data('occupancy')
# Specify the features of interest and the classes of the target
features = ["temperature", "relative humidity", "light", "C02", "humidity"]
classes = ['unoccupied', 'occupied']
# Extract the numpy arrays from the data frame
X = data[features]
y = data.occupancy
visualizer = ScatterVisualizer(x='light', y='C02', classes=classes)
visualizer.fit(X, y)
visualizer.transform(X)
visualizer.poof()
# Load the data
df = load_data('concrete')
feature = 'cement'
target = 'strength'
# Get the X and y data from the DataFrame
X = df[feature]
y = df[target]
visualizer = JointPlotVisualizer(feature=feature, target=target)
visualizer.fit(X, y)
visualizer.poof()
visualizer = JointPlotVisualizer(feature=feature,
target=target,
joint_plot='hex')
visualizer.fit(X, y)
visualizer.poof()
def showRank2D():
# Load the dataset
data = load_data('credit')
# Specify the features of interest
features = [
'limit',
'sex',
'edu',
'married',
'age',
'apr_delay',
'may_delay',
'jun_delay',
'jul_delay',
'aug_delay',
'sep_delay',
'apr_bill',
'may_bill',
'jun_bill',
'jul_bill',
'aug_bill',
'sep_bill',
'apr_pay',
'may_pay',
'jun_pay',
'jul_pay',
'aug_pay',
'sep_pay',
]
# Extract the numpy arrays from the data frame
X = data[features].as_matrix()
y = data.default.as_matrix()
# Instantiate the visualizer with the Covariance ranking algorithm
visualizer = Rank2D(features=features, algorithm='pearson')
visualizer.fit(X, y) # Fit the data to the visualizer
visualizer.transform(X) # Transform the data
visualizer.poof() # Draw/show/poof the data
def showPCAProjection():
# Load the classification data set
data = load_data('credit')
# Specify the features of interest
features = [
'limit',
'sex',
'edu',
'married',
'age',
'apr_delay',
'may_delay',
'jun_delay',
'jul_delay',
'aug_delay',
'sep_delay',
'apr_bill',
'may_bill',
'jun_bill',
'jul_bill',
'aug_bill',
'sep_bill',
'apr_pay',
'may_pay',
'jun_pay',
'jul_pay',
'aug_pay',
'sep_pay',
]
# Extract the numpy arrays from the data frame
X = data[features].as_matrix()
y = data.default.as_matrix()
visualizer = PCADecomposition(scale=True, center=False, col=y)
visualizer.fit_transform(X, y)
visualizer.poof()
visualizer = PCADecomposition(scale=True, center=False, col=y, proj_dim=3)
visualizer.fit_transform(X, y)
visualizer.poof()
def showError():
# Load the data
df = load_data('concrete')
feature_names = [
'cement', 'slag', 'ash', 'water', 'splast', 'coarse', 'fine', 'age'
]
target_name = 'strength'
# Get the X and y data from the DataFrame
X = df[feature_names].as_matrix()
y = df[target_name].as_matrix()
# Create the train and test data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
# Instantiate the linear model and visualizer
lasso = Lasso()
visualizer = PredictionError(lasso)
visualizer.fit(X_train, y_train) # Fit the training data to the visualizer
visualizer.score(X_test, y_test) # Evaluate the model on the test data
g = visualizer.poof() # Draw/show/poof the data
def showROC():
# Load the classification data set
data = load_data('occupancy')
# Specify the features of interest and the classes of the target
features = ["temperature", "relative humidity", "light", "C02", "humidity"]
classes = ['unoccupied', 'occupied']
# Extract the numpy arrays from the data frame
X = data[features].as_matrix()
y = data.occupancy.as_matrix()
# Create the train and test data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
# Instantiate the classification model and visualizer
logistic = LogisticRegression()
visualizer = ROCAUC(logistic)
visualizer.fit(X_train, y_train) # Fit the training data to the visualizer
visualizer.score(X_test, y_test) # Evaluate the model on the test data
g = visualizer.poof() # Draw/show/poof the data