def test_parallel_coords(pandas=False, outpath=None):
"""
Runs the parallel coordinates visualizer on the dataset.
Parameters
----------
pandas : bool
Run the pandas version of the function
outpath : path or None
Save the figure to disk rather than show (if None)
"""
data = load_data('occupancy') # Load the data
features = ['temp', 'humid', 'light', 'co2', 'hratio']
classes = ['unoccupied', 'occupied']
X = data[features].as_matrix()
y = data.occupied.as_matrix()
if pandas:
parallel_coordinates(data[features + ['occupied']], 'occupied')
if outpath:
plt.savefig(outpath)
else:
plt.show()
else:
visualizer = ParallelCoordinates( # Instantiate the visualizer
classes=classes, features=features)
visualizer.fit(X, y) # Fit the data to the visualizer
visualizer.transform(X) # Transform the data
visualizer.poof(outpath=outpath) # Draw/show/poof the data
def pcoords(X, y, outpath, **kwargs):
# Create a new figure and axes
_, ax = plt.subplots()
# Create the visualizer
visualizer = ParallelCoordinates(ax=ax, **kwargs)
visualizer.fit_transform(X, y)
# Save to disk
visualizer.poof(outpath=outpath)
def pcoords(X, y, outpath, **kwargs):
# Create a new figure and axes
_, ax = plt.subplots()
# Create the visualizer
visualizer = ParallelCoordinates(ax=ax, **kwargs)
visualizer.fit_transform(X, y)
# Save to disk
visualizer.poof(outpath=outpath)
def pcoords(X, y, outpath, **kwargs):
# Create a new figure and axes
fig = plt.figure()
ax = fig.add_subplot(111)
# Create the visualizer
visualizer = ParallelCoordinates(**kwargs)
visualizer.fit(X, y)
visualizer.transform(X)
# Save to disk
visualizer.poof(outpath=outpath)
# normalize data to 0-1 range
for feature in num_features:
data_norm[feature] = (data[feature] - data[feature].mean(skipna=True)) / (
data[feature].max(skipna=True) - data[feature].min(skipna=True))
# Extract the numpy arrays from the data frame
X = data_norm[num_features].to_numpy()
y = data.Survived.to_numpy()
# Instantiate the visualizer
# Instantiate the visualizer
visualizer = ParallelCoordinates(classes=classes, features=num_features)
visualizer.fit(X, y) # Fit the data to the visualizer
visualizer.transform(X) # Transform the data
visualizer.poof(outpath="d://pcoords2.png") # Draw/show/poof the data
plt.show()
# Step 10 - stacked bar charts to compare survived/not survived
# set up the figure size
# %matplotlib inline
plt.rcParams['figure.figsize'] = (20, 10)
# make subplots
fig, axes = plt.subplots(nrows=2, ncols=2)
# make the data read to feed into the visulizer
Sex_survived = data.replace({'Survived': {
1: 'Survived',
0: 'Not-survived'
}})[data['Survived'] == 1]['Sex'].value_counts()
for feature in num_features:
data_norm[feature] = (data[feature] - data[feature].mean(skipna=True)) / (
data[feature].max(skipna=True) - data[feature].min(skipna=True))
# Extract the numpy arrays from the data frame
# X = data_norm[num_features].as_matrix()
# y = data.Survived.as_matrix()
X = data_norm[num_features].to_numpy()
y = data.BendCurve.to_numpy()
# Instantiate the visualizer
visualizer = ParallelCoordinates(classes=classes, features=num_features)
visualizer.fit(X, y) # Fit the data to the visualizer
visualizer.transform(X) # Transform the data
visualizer.poof(outpath="pcoords2.png") # Draw/show/poof the data
plt.show()
print("Starting Step 10 Here ")
# Step 10 - stacked bar charts to compare survived/not survived
#set up the figure size
#%matplotlib inline
plt.rcParams['figure.figsize'] = (20, 10)
# make subplots
fig, axes = plt.subplots(nrows=2, ncols=2)
# make the data read to feed into the visulizer
Sex_survived = data.replace(
{'BendCurve': {
1: 'BendCurve',
from sklearn.datasets import load_iris
data = load_iris()
data
import pandas as pd
pd.read_csv(data.filename)
from yellowbrick.features import ParallelCoordinates
viz = ParallelCoordinates(features=data.feature_names,
classes=data.target_names,
normalize='standard')
viz.fit(data.data, data.target)
viz.transform(data.data)
viz.poof()
from sklearn.tree import DecisionTreeClassifier
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
X, y = data.data, data.target
X_train, X_test, y_train, y_test = train_test_split(X, y)
scaler = StandardScaler()
scaler.fit(X_train)
X1 = scaler.transform(X_train)
clf = DecisionTreeClassifier()
clf.fit(X1, y_train)
X2 = scaler.transform(X_test)
clf.predict(X2)
from sklearn.pipeline import Pipeline
decision_pipeline = Pipeline([
('normalize', StandardScaler()),
('decision', DecisionTreeClassifier())
])
decision_pipeline.fit(X_train, y_train)
#and then creates the confusion_matrix from scikit learn.
cm.score(X_val, y_val)
# change fontsize of the labels in the figure
for label in cm.ax.texts:
label.set_size(20)
#How did we do?
cm.show(outpath="cmdata.png")
# Precision, Recall, and F1 Score
# set the size of the figure and the font size
#%matplotlib inline
plt.rcParams['figure.figsize'] = (15, 7)
plt.rcParams['font.size'] = 20
# Instantiate the visualizer
visualizer = ClassificationReport(model, classes=classes)
visualizer.fit(X_train, y_train) # Fit the training data to the visualizer
visualizer.score(X_val, y_val) # Evaluate the model on the test data
g = visualizer.poof()
# ROC and AUC
#Instantiate the visualizer
visualizer = ROCAUC(model)
visualizer.fit(X_train, y_train) # Fit the training data to the visualizer
visualizer.score(X_val, y_val) # Evaluate the model on the test data
g = visualizer.poof()