数据探索很麻烦？推荐一款史上最强大的特征分析可视化工具：yellowbrick

# 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 instances and target
X = data[features]
y = data.occupancy

# Import the visualizer
from yellowbrick.features import RadViz

# Instantiate the visualizer
visualizer = RadViz(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

from yellowbrick.features import Rank1D

# Instantiate the 1D visualizer with the Sharpiro ranking algorithm
visualizer = Rank1D(features=features, algorithm='shapiro')

visualizer.fit(X, y)                # Fit the data to the visualizer
visualizer.transform(X)             # Transform the data
visualizer.poof()                   # Draw/show/poof the data

# Load the classification data set
data = load_data('concrete')

# Specify the features of interest and the target
target = "strength"
features = [
    'cement', 'slag', 'ash', 'water', 'splast', 'coarse', 'fine', 'age'
]

# Extract the instance data and the target
X = data[features]
y = data[target]

visualizer = PCADecomposition(scale=True, proj_features=True)
visualizer.fit_transform(X, y)
visualizer.poof()

import matplotlib.pyplot as plt

from sklearn.ensemble import GradientBoostingClassifier

from yellowbrick.features.importances import FeatureImportances

# Create a new matplotlib figure
fig = plt.figure()
ax = fig.add_subplot()

viz = FeatureImportances(GradientBoostingClassifier(), ax=ax)
viz.fit(X, y)
viz.poof()

from sklearn.svm import SVC
from sklearn.datasets import make_classification

from yellowbrick.features import RFECV

# Create a dataset with only 3 informative features
X, y = make_classification(
    n_samples=1000, n_features=25, n_informative=3, n_redundant=2,
    n_repeated=0, n_classes=8, n_clusters_per_class=1, random_state=0
)

# Create RFECV visualizer with linear SVM classifier
viz = RFECV(SVC(kernel='linear', C=1))
viz.fit(X, y)
viz.poof()

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import StratifiedKFold

df = load_data('credit')

target = 'default'
features = [col for col in data.columns if col != target]

X = data[features]
y = data[target]

cv = StratifiedKFold(5)
oz = RFECV(RandomForestClassifier(), cv=cv, scoring='f1_weighted')

oz.fit(X, y)
oz.poof()

from sklearn.linear_model import Ridge
from yellowbrick.regressor import ResidualsPlot

# Instantiate the linear model and visualizer
ridge = Ridge()
visualizer = ResidualsPlot(ridge)

visualizer.fit(X_train, y_train)  # Fit the training data to the model
visualizer.score(X_test, y_test)  # Evaluate the model on the test data
visualizer.poof()                 # Draw/show/poof the data

import numpy as np

from sklearn.linear_model import LassoCV
from yellowbrick.regressor import AlphaSelection

# Create a list of alphas to cross-validate against
alphas = np.logspace(-10, 1, 400)

# Instantiate the linear model and visualizer
model = LassoCV(alphas=alphas)
visualizer = AlphaSelection(model)

visualizer.fit(X, y)
g = visualizer.poof()

from sklearn.ensemble import RandomForestClassifier

from yellowbrick.classifier import ClassPredictionError

# Instantiate the classification model and visualizer
visualizer = ClassPredictionError(
    RandomForestClassifier(), classes=classes
)

# Fit the training data to the visualizer
visualizer.fit(X_train, y_train)

# Evaluate the model on the test data
visualizer.score(X_test, y_test)

# Draw visualization
g = visualizer.poof()

from sklearn.linear_model import LogisticRegression
from yellowbrick.classifier import DiscriminationThreshold

# Instantiate the classification model and visualizer
logistic = LogisticRegression()
visualizer = DiscriminationThreshold(logistic)

visualizer.fit(X, y)  # Fit the training data to the visualizer
visualizer.poof()     # Draw/show/poof the data

from sklearn.datasets import make_blobs

# Create synthetic dataset with 8 random clusters
X, y = make_blobs(centers=8, n_features=12, shuffle=True, random_state=42)

from sklearn.cluster import KMeans
from yellowbrick.cluster import KElbowVisualizer

# Instantiate the clustering model and visualizer
model = KMeans()
visualizer = KElbowVisualizer(model, k=(4,12))

visualizer.fit(X)    # Fit the data to the visualizer
visualizer.poof()    # Draw/show/poof the data

from sklearn.datasets import make_blobs

# Make 12 blobs dataset
X, y = make_blobs(centers=12, n_samples=1000, n_features=16, shuffle=True)

from sklearn.cluster import KMeans
from yellowbrick.cluster import InterclusterDistance

# Instantiate the clustering model and visualizer
visualizer = InterclusterDistance(KMeans(9))

visualizer.fit(X) # Fit the training data to the visualizer
visualizer.poof() # Draw/show/poof the data

import numpy as np

from sklearn.tree import DecisionTreeRegressor
from yellowbrick.model_selection import ValidationCurve

# Load a regression dataset
data = load_data('energy')

# Specify features of interest and the target
targets = ["heating load", "cooling load"]
features = [col for col in data.columns if col not in targets]

# Extract the instances and target
X = data[features]
y = data[targets[0]]

viz = ValidationCurve(
    DecisionTreeRegressor(), param_name="max_depth",
    param_range=np.arange(1, 11), cv=10, scoring="r2"
)

# Fit and poof the visualizer
viz.fit(X, y)
viz.poof()