def main():
cal_housing = fetch_california_housing()
# split 80/20 train-test
X_train, X_test, y_train, y_test = train_test_split(cal_housing.data,
cal_housing.target,
test_size=0.2,
random_state=1)
names = cal_housing.feature_names
print('_' * 80)
print("Training GBRT...")
clf = GradientBoostingRegressor(n_estimators=100,
max_depth=4,
learning_rate=0.1,
loss='huber',
random_state=1)
clf.fit(X_train, y_train)
print("done.")
print('_' * 80)
print('Convenience plot with ``partial_dependence_plots``')
print
features = [0, 5, 1, 2, (5, 1)]
fig, axs = plot_partial_dependence(clf,
X_train,
features,
feature_names=names,
n_jobs=3,
grid_resolution=50)
fig.suptitle(
'Partial dependence of house value on nonlocation features for the California housing dataset'
)
plt.subplots_adjust(top=0.9)
print('_' * 80)
print('Custom 3d plot via ``partial_dependence``')
print
fig = plt.figure()
target_feature = (1, 5)
pdp, (x_axis, y_axis) = partial_dependence(clf,
target_feature,
X=X_train,
grid_resolution=50)
XX, YY = np.meshgrid(x_axis, y_axis)
Z = pdp.T.reshape(XX.shape).T
ax = Axes3D(fig)
surf = ax.plot_surface(XX, YY, Z, rstride=1, cstride=1, cmap=plt.cm.BuPu)
ax.set_xlabel(names[target_feature[0]])
ax.set_ylabel(names[target_feature[1]])
ax.set_zlabel('Partial dependence')
# pretty init view
ax.view_init(elev=22, azim=122)
plt.colorbar(surf)
plt.suptitle(
'Partial dependence of house value on median age and average occupancy'
)
plt.subplots_adjust(top=0.9)
plt.show()
def test():
# data
cal_housing = fetch_california_housing()
X = cal_housing['data']
Y = np.reshape(cal_housing['target'], (-1, 1))
# train models
iters = 100
name = ["0", "1", "2", "3", "4"]
model = [
SCNN(8, 1, 0, update=Update.Rprop()),
SCNN(8, 1, 1, update=Update.Rprop()),
SCNN(8, 1, 2, update=Update.Rprop()),
SCNN(8, 1, 3, update=Update.Rprop()),
SCNN(8, 1, 4, update=Update.Rprop())
]
error = np.zeros((len(model), iters))
for i in range(iters):
for m in range(len(model)):
error[m, i] = model[m].partial_fit(X, Y)
print(i + 1, "complete")
# plot results
plt.figure()
plt.title('Error Curves')
for m in range(len(model)):
plt.semilogy(error[m], label=name[m])
plt.legend()
plt.show()
def test_abs_loss():
X, y = california_housing.fetch_california_housing(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y)
regressor = GradientBooster(n_iter=100, loss_function=AbsoluteLoss())
regressor.fit(X_train, y_train)
y_pred = regressor.predict(X_test)
print(f"Test Mean absolute error: {mean_absolute_error(y_pred, y_test):.4f}")
def main():
# fetch California housing dataset
try:
cal_housing = fetch_california_housing()
except HTTPError:
print("Failed downloading california housing data.")
return
# split 80/20 train-test
X_train, X_test, y_train, y_test = train_test_split(cal_housing.data,
cal_housing.target,
test_size=0.2,
random_state=1)
names = cal_housing.feature_names
print('_' * 80)
print("Training GBRT...")
clf = GradientBoostingRegressor(n_estimators=100, max_depth=4,
learning_rate=0.1, loss='huber',
random_state=1)
clf.fit(X_train, y_train)
print("done.")
print('_' * 80)
print('Convenience plot with ``partial_dependence_plots``')
print
features = [0, 5, 1, 2, (5, 1)]
fig, axs = plot_partial_dependence(clf, X_train, features, feature_names=names,
n_jobs=3, grid_resolution=50)
fig.suptitle('Partial dependence of house value on nonlocation features\n'
'for the California housing dataset')
plt.subplots_adjust(top=0.9) # tight_layout causes overlap with suptitle
print('_' * 80)
print('Custom 3d plot via ``partial_dependence``')
print
fig = plt.figure()
target_feature = (1, 5)
pdp, (x_axis, y_axis) = partial_dependence(clf, target_feature,
X=X_train, grid_resolution=50)
XX, YY = np.meshgrid(x_axis, y_axis)
Z = pdp.T.reshape(XX.shape).T
ax = Axes3D(fig)
surf = ax.plot_surface(XX, YY, Z, rstride=1, cstride=1, cmap=plt.cm.BuPu)
ax.set_xlabel(names[target_feature[0]])
ax.set_ylabel(names[target_feature[1]])
ax.set_zlabel('Partial dependence')
# pretty init view
ax.view_init(elev=22, azim=122)
plt.colorbar(surf)
plt.suptitle('Partial dependence of house value on median age and '
'average occupancy')
plt.subplots_adjust(top=0.9)
plt.show()
def generate_house_data():
from sklearn.datasets.california_housing import fetch_california_housing
from sklearn.preprocessing import StandardScaler
houses = fetch_california_housing()
scaler = StandardScaler()
scaled_data = scaler.fit_transform(houses.data)
X_train, X_val, Y_train, Y_val = train_test_split(scaled_data,
houses.target)
print('Train data shape', X_train.shape)
print('Validation data shape', X_val.shape)
return X_train, X_val, Y_train, Y_val
def gbm_monotone_smoke_test():
cal_housing = fetch_california_housing()
data = h2o.H2OFrame(cal_housing.data, column_names=cal_housing.feature_names)
data["target"] = h2o.H2OFrame(cal_housing.target)
train, test = data.split_frame([0.6], seed=123)
feature_names = ['MedInc', 'AveOccup', 'HouseAge']
monotone_constraints = {"MedInc": 1, "AveOccup": -1, "HouseAge": 1}
gbm_mono = H2OGradientBoostingEstimator(monotone_constraints=monotone_constraints, seed=42)
gbm_mono.train(x=feature_names, y="target", training_frame=train, validation_frame=test)
def gbm_monotone_smoke_test():
cal_housing = fetch_california_housing()
data = h2o.H2OFrame(cal_housing.data,
column_names=cal_housing.feature_names)
data["target"] = h2o.H2OFrame(cal_housing.target)
train, test = data.split_frame([0.6], seed=123)
feature_names = ['MedInc', 'AveOccup', 'HouseAge']
monotone_constraints = {"MedInc": 1, "AveOccup": -1, "HouseAge": 1}
gbm_mono = H2OGradientBoostingEstimator(
monotone_constraints=monotone_constraints, seed=42)
gbm_mono.train(x=feature_names,
y="target",
training_frame=train,
validation_frame=test)
def test_weighted_nurturing():
# X1 = np.arange(0, 10, 0.1)
# X2 = np.arange(10, 20, 0.1)
# y_train = np.sin(X1).ravel() + np.cos(X2).ravel()
# X_train = pd.DataFrame(np.array([X1, X2]).T, columns=['x1', 'x2'])
# X_test, y_test = X_train, y_train
cal_housing = fetch_california_housing()
X_train, X_test, y_train, y_test = \
train_test_split(cal_housing.data, cal_housing.target,
test_size=0.3, random_state=5)
X_train = pd.DataFrame(X_train, columns=cal_housing.feature_names)
X_test = pd.DataFrame(X_test, columns=cal_housing.feature_names)
model_params = {
'max_depth': 10, 'n_estimators': 200, 'random_state': 5,
'n_jobs': -1, 'bootstrap': True,
}
with StopWatch('weighted nurturing'):
nurtured_ensemble = weighted_nurturing(
RandomForestRegressor, X_train, y_train,
feature_names=X_train.columns,
n_iterations=20, metric_function='mse',
n_tunes=50, update_weight=0.3,
model_params=model_params)
print("The mean-squared error for nurtured ensemble prediction: {}".format(
mean_squared_error(nurtured_ensemble.predict(X_test), y_test)))
# plain_rf = RandomForestRegressor(
# min_samples_leaf=100, max_depth=8,
# n_estimators=1000, random_state=5, n_jobs=-1)
plain_params = {'random_state': 5, }
plain_rf = RandomForestRegressor(n_estimators=3000, max_depth=8, n_jobs=-1, **plain_params)
plain_rf.fit(X_train, y_train)
plain_gbr = GradientBoostingRegressor(
n_estimators=1000, max_depth=5, **plain_params)
plain_gbr.fit(X_train, y_train)
print("The mean-squared error for plain RandomForest prediction: {}".format(
mean_squared_error(plain_rf.predict(X_test), y_test)))
print("The mean-squared error for plain GradientBoost prediction: {}".format(
mean_squared_error(plain_gbr.predict(X_test), y_test)))
run_id,experiment_id,experiment_name,run_id,metric,run_mode = create_predict_widgets(exp_name,metrics) run_id,experiment_id,experiment_name,run_id,metric,run_mode,exp_name # COMMAND ---------- dump_run_id(run_id) # COMMAND ---------- # MAGIC %md ### Read data # COMMAND ---------- from sklearn.datasets.california_housing import fetch_california_housing data = fetch_california_housing().data # COMMAND ---------- # MAGIC %md ### Review the MLflow UI # COMMAND ---------- display_run_uri(experiment_id, run_id) # COMMAND ---------- # MAGIC %md ### Predict # MAGIC # MAGIC Let's now register our Keras model as a Spark UDF to apply to rows in parallel.
from sklearn.datasets.california_housing import fetch_california_housing
from sklearn.model_selection import train_test_split
import pandas as pd
import matplotlib.pyplot as plt
from sklearn import preprocessing
import numpy as np
from sklearn.neighbors import BallTree
## --------- create dataframe, add .target ----------
dataset = fetch_california_housing()
df = pd.DataFrame(dataset.data, columns=dataset.feature_names)
df['target'] = pd.Series(dataset.target)
## --------- 2 features chosen for training ---------
X = df[['Population', 'HouseAge']]
print('_____________________________________')
print('Dataset before train split')
print(X.describe())
y = df.target
## ------------- split for train & test -------------
X_train, X_test, y_train, y_test = train_test_split(X,
y,
random_state=10,
test_size=0.2)
df2 = pd.DataFrame(data=X_train, columns=['Population', 'HouseAge'])
## ---------------- feature distance ----------------
import importlib
packages = [
'pandas', 'IPython', 'statsmodels', 'sklearn', 'seaborn', 'requests',
'scipy', 'notebook'
]
bad = []
for package in packages:
try:
importlib.import_module(package)
except ImportError:
bad.append("Can't import %s" % package)
else:
if len(bad) > 0:
print('\n'.join(bad))
else:
from sklearn.datasets import california_housing
print("Caching california_housing")
data = california_housing.fetch_california_housing()
print("All good. Enjoy the tutorial!")
def main():
cal_housing = fetch_california_housing()
X, y = cal_housing.data, cal_housing.target
names = cal_housing.feature_names
# Center target to avoid gradient boosting init bias: gradient boosting
# with the 'recursion' method does not account for the initial estimator
# (here the average target, by default)
y -= y.mean()
print("Training MLPRegressor...")
est = MLPRegressor(activation='logistic')
est.fit(X, y)
print('Computing partial dependence plots...')
# We don't compute the 2-way PDP (5, 1) here, because it is a lot slower
# with the brute method.
features = [0, 5, 1, 2]
plot_partial_dependence(est,
X,
features,
feature_names=names,
n_jobs=3,
grid_resolution=50)
fig = plt.gcf()
fig.suptitle('Partial dependence of house value on non-location features\n'
'for the California housing dataset, with MLPRegressor')
plt.subplots_adjust(top=0.9) # tight_layout causes overlap with suptitle
print("Training GradientBoostingRegressor...")
est = GradientBoostingRegressor(n_estimators=100,
max_depth=4,
learning_rate=0.1,
loss='huber',
random_state=1)
est.fit(X, y)
print('Computing partial dependence plots...')
features = [0, 5, 1, 2, (5, 1)]
plot_partial_dependence(est,
X,
features,
feature_names=names,
n_jobs=3,
grid_resolution=50)
fig = plt.gcf()
fig.suptitle('Partial dependence of house value on non-location features\n'
'for the California housing dataset, with Gradient Boosting')
plt.subplots_adjust(top=0.9)
print('Custom 3d plot via ``partial_dependence``')
fig = plt.figure()
target_feature = (1, 5)
pdp, axes = partial_dependence(est, X, target_feature, grid_resolution=50)
XX, YY = np.meshgrid(axes[0], axes[1])
Z = pdp[0].T
ax = Axes3D(fig)
surf = ax.plot_surface(XX,
YY,
Z,
rstride=1,
cstride=1,
cmap=plt.cm.BuPu,
edgecolor='k')
ax.set_xlabel(names[target_feature[0]])
ax.set_ylabel(names[target_feature[1]])
ax.set_zlabel('Partial dependence')
# pretty init view
ax.view_init(elev=22, azim=122)
plt.colorbar(surf)
plt.suptitle('Partial dependence of house value on median\n'
'age and average occupancy, with Gradient Boosting')
plt.subplots_adjust(top=0.9)
plt.show()
def ml_GradientBoostingClassifier2(self):
# This example shows how to obtain partial dependence plots from a GradientBoostingRegressor trained on the California housing dataset.
cal_housing = fetch_california_housing()
# split 80/20 train-tests
X_train, X_test, y_train, y_test = train_test_split(cal_housing.data,
cal_housing.target,
test_size=0.2,
random_state=1)
names = cal_housing.feature_names
print("Training GBRT...")
clf = GradientBoostingRegressor(n_estimators=100,
max_depth=4,
learning_rate=0.1,
loss='huber',
random_state=1)
clf.fit(X_train, y_train)
print(" done.")
print('Convenience plot with ``partial_dependence_plots``')
features = [0, 5, 1, 2, (5, 1)]
fig, axs = plot_partial_dependence(clf,
X_train,
features,
feature_names=names,
n_jobs=3,
grid_resolution=50)
fig.suptitle(
'Partial dependence of house value on nonlocation features\n'
'for the California housing dataset')
plt.subplots_adjust(
top=0.9) # tight_layout causes overlap with suptitle
print('Custom 3d plot via ``partial_dependence``')
fig = plt.figure()
target_feature = (1, 5)
pdp, axes = partial_dependence(clf,
target_feature,
X=X_train,
grid_resolution=50)
XX, YY = np.meshgrid(axes[0], axes[1])
Z = pdp[0].reshape(list(map(np.size, axes))).T
ax = Axes3D(fig)
surf = ax.plot_surface(XX,
YY,
Z,
rstride=1,
cstride=1,
cmap=plt.cm.BuPu,
edgecolor='k')
ax.set_xlabel(names[target_feature[0]])
ax.set_ylabel(names[target_feature[1]])
ax.set_zlabel('Partial dependence')
# pretty init view
ax.view_init(elev=22, azim=122)
plt.colorbar(surf)
plt.suptitle('Partial dependence of house value on median\n'
'age and average occupancy')
plt.subplots_adjust(top=0.9)
plt.show()
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2018/7/31 0031 20:35
# @Author : Shulin Liu
from sklearn.datasets.california_housing import fetch_california_housing
from sklearn import tree
import pydotplus
from IPython.display import Image
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.ensemble import RandomForestRegressor
house = fetch_california_housing()
print(house.DESCR)
dtr = tree.DecisionTreeRegressor(max_depth=2) # 决策树的最大深度为2
dtr.fit(house.data[:, [6, 7]], house.target)
'''
决策树可视化
'''
dot_data = tree.export_graphviz(dtr,
out_file=None,
feature_names=house.feature_names[6:8],
filled=True,
impurity=False,
rounded=True)
graph = pydotplus.graph_from_dot_data(dot_data)
graph.get_nodes()[7].set_fillcolor("#FFF2DD")
Image(graph.create_png())
graph.write_png('dtr_white_background.png')
'''
def main():
cal_housing = fetch_california_housing()
X, y = cal_housing.data, cal_housing.target
names = cal_housing.feature_names
# Center target to avoid gradient boosting init bias: gradient boosting
# with the 'recursion' method does not account for the initial estimator
# (here the average target, by default)
y -= y.mean()
print("Training SNN_Regressor...")
est = SNN_Regressor(8,
1,
10,
10,
hiddenAct=Activation.Tanh(),
error=Error.Mse(),
update=Update.RmsProp(0.001, rateDecay=0.9))
t = [
(3, lambda e: e.cool()), # cool
(6, lambda e: Trainer.prune(e, X, y)), # prune
# ( 18, lambda e: e.cool() ), # cool
(9,
lambda e: Trainer.grow(e, max(1, 1 + int(np.log(e.hiddenSize_ + 1))))
), # grow
# ( 11, lambda e: e.cool() ), # cool
]
growLoss = Trainer.train(est, X, y, batch=1, maxIter=100, triggers=t)
est.maxIter_ = 1000
plt.semilogy(growLoss, label='Grow')
plt.legend()
# plt.show()
# pdb.set_trace()
print("SNN weights:", est.weight_)
print("SNN dweight:", est.dWeight_)
print("SNN nHidden:", est.hiddenSize_)
print('Computing partial dependence plots...')
# We don't compute the 2-way PDP (5, 1) here, because it is a lot slower
# with the brute method.
features = [0, 5, 1, 2]
plot_partial_dependence(est,
X,
features,
feature_names=names,
n_jobs=3,
grid_resolution=50)
fig = plt.gcf()
fig.suptitle('Partial dependence of house value on non-location features\n'
'for the California housing dataset, with SNN_Regressor...')
plt.subplots_adjust(top=0.9) # tight_layout causes overlap with suptitle
print("Training MLPRegressor...")
est = MLPRegressor(activation='logistic')
est.fit(X, y)
print('MLP Loss: ', np.average(Error.Mse().f(y, est.predict(X))))
print('Computing partial dependence plots...')
# We don't compute the 2-way PDP (5, 1) here, because it is a lot slower
# with the brute method.
features = [0, 5, 1, 2]
plot_partial_dependence(est,
X,
features,
feature_names=names,
n_jobs=3,
grid_resolution=50)
fig = plt.gcf()
fig.suptitle('Partial dependence of house value on non-location features\n'
'for the California housing dataset, with MLPRegressor')
plt.subplots_adjust(top=0.9) # tight_layout causes overlap with suptitle
print("Training GradientBoostingRegressor...")
est = GradientBoostingRegressor(n_estimators=100,
max_depth=4,
learning_rate=0.1,
loss='huber',
random_state=1)
est.fit(X, y)
print('Computing partial dependence plots...')
features = [0, 5, 1, 2, (5, 1)]
plot_partial_dependence(est,
X,
features,
feature_names=names,
n_jobs=3,
grid_resolution=50)
fig = plt.gcf()
fig.suptitle('Partial dependence of house value on non-location features\n'
'for the California housing dataset, with Gradient Boosting')
plt.subplots_adjust(top=0.9)
print('Custom 3d plot via ``partial_dependence``')
fig = plt.figure()
target_feature = (1, 5)
pdp, axes = partial_dependence(est, X, target_feature, grid_resolution=50)
XX, YY = np.meshgrid(axes[0], axes[1])
Z = pdp[0].T
ax = Axes3D(fig)
surf = ax.plot_surface(XX,
YY,
Z,
rstride=1,
cstride=1,
cmap=plt.cm.BuPu,
edgecolor='k')
ax.set_xlabel(names[target_feature[0]])
ax.set_ylabel(names[target_feature[1]])
ax.set_zlabel('Partial dependence')
# pretty init view
ax.view_init(elev=22, azim=122)
plt.colorbar(surf)
plt.suptitle('Partial dependence of house value on median\n'
'age and average occupancy, with Gradient Boosting')
plt.subplots_adjust(top=0.9)
plt.show()
def main():
cal_housing = fetch_california_housing()
X, y = cal_housing.data, cal_housing.target
names = cal_housing.feature_names
# Center target to avoid gradient boosting init bias: gradient boosting
# with the 'recursion' method does not account for the initial estimator
# (here the average target, by default)
y -= y.mean()
print("Training MLPRegressor...")
est = MLPRegressor(activation='logistic')
est.fit(X, y)
print('Computing partial dependence plots...')
# We don't compute the 2-way PDP (5, 1) here, because it is a lot slower
# with the brute method.
features = [0, 5, 1, 2]
plot_partial_dependence(est, X, features, feature_names=names,
n_jobs=3, grid_resolution=50)
fig = plt.gcf()
fig.suptitle('Partial dependence of house value on non-location features\n'
'for the California housing dataset, with MLPRegressor')
plt.subplots_adjust(top=0.9) # tight_layout causes overlap with suptitle
print("Training GradientBoostingRegressor...")
est = GradientBoostingRegressor(n_estimators=100, max_depth=4,
learning_rate=0.1, loss='huber',
random_state=1)
est.fit(X, y)
print('Computing partial dependence plots...')
features = [0, 5, 1, 2, (5, 1)]
plot_partial_dependence(est, X, features, feature_names=names,
n_jobs=3, grid_resolution=50)
fig = plt.gcf()
fig.suptitle('Partial dependence of house value on non-location features\n'
'for the California housing dataset, with Gradient Boosting')
plt.subplots_adjust(top=0.9)
print('Custom 3d plot via ``partial_dependence``')
fig = plt.figure()
target_feature = (1, 5)
pdp, axes = partial_dependence(est, X, target_feature,
grid_resolution=50)
XX, YY = np.meshgrid(axes[0], axes[1])
Z = pdp[0].T
ax = Axes3D(fig)
surf = ax.plot_surface(XX, YY, Z, rstride=1, cstride=1,
cmap=plt.cm.BuPu, edgecolor='k')
ax.set_xlabel(names[target_feature[0]])
ax.set_ylabel(names[target_feature[1]])
ax.set_zlabel('Partial dependence')
# pretty init view
ax.view_init(elev=22, azim=122)
plt.colorbar(surf)
plt.suptitle('Partial dependence of house value on median\n'
'age and average occupancy, with Gradient Boosting')
plt.subplots_adjust(top=0.9)
plt.show()
def setUp(self):
self.dataset = fetch_california_housing()
"""
print(__doc__)
import numpy as np
import pylab as pl
from mpl_toolkits.mplot3d import Axes3D
from sklearn.cross_validation import train_test_split
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.ensemble.partial_dependence import plot_partial_dependence
from sklearn.ensemble.partial_dependence import partial_dependence
from sklearn.datasets.california_housing import fetch_california_housing
# fetch California housing dataset
cal_housing = fetch_california_housing()
# split 80/20 train-test
X_train, X_test, y_train, y_test = train_test_split(cal_housing.data,
cal_housing.target,
test_size=0.2,
random_state=1)
names = cal_housing.feature_names
print('_' * 80)
print("Training GBRT...")
clf = GradientBoostingRegressor(n_estimators=100, max_depth=4,
learning_rate=0.1, loss='huber',
random_state=1)
clf.fit(X_train, y_train)
print("done.")
import importlib
packages = ["pandas", "IPython", "statsmodels", "sklearn", "seaborn", "toolz", "bs4", "requests", "scipy", "tables"]
bad = []
for package in packages:
try:
importlib.import_module(package)
except ImportError:
bad.append("Can't import %s" % package)
else:
if len(bad) > 0:
print("\n".join(bad))
else:
from sklearn.datasets import california_housing
print("Caching california_housing")
data = california_housing.fetch_california_housing()
print("All good. Enjoy the tutorial!")
def __init__(self):
self.data = california_housing.fetch_california_housing()
self.X_train, self.X_test, self.y_train, self.y_test =\
train_test_split(self.data.data,self.data.target,random_state=42,test_size=0.2)
""" for stuff on techniques used for mnist http://yann.lecun.com/exdb/mnist/ """ from sklearn.datasets import load_digits from sklearn.datasets.california_housing import fetch_california_housing # write data into ./mldata/mnist-original.mat mnist = load_digits(return_X_y=True) housing = fetch_california_housing(data_home='.')
#!/usr/bin/env python 3.6 # -*- coding: utf-8 -*- """ # @Company ：华中科技大学机械学院数控中心 # @version : V1.0 # @Author : lizhaofu # @contact : [email protected] 2018--2022 # @Time : 2019/11/27 16:27 # @File : decision_tree_regression_visualization.py # @Software: PyCharm """ from sklearn.datasets.california_housing import fetch_california_housing import pydotplus housing = fetch_california_housing() ###调用sklearn自带的数集 # print(housing.DESCR) print(housing.data.shape) print(housing.data[1]) print(len(housing.data[1])) print(housing.feature_names) print(housing.target) #####取要使用的特征做决策树 from sklearn import tree dtr = tree.DecisionTreeRegressor(max_depth=4) dtr.fit(housing.data[:, [3, 4, 5, 6, 7]], housing.target) ###取房子所在的经度和纬度 ###输出构造决策树模型的一些基本参数，有些事默认的 print(dtr)
def get_datas(self):
"""
获取加利福尼亚的房屋信息
"""
housing = fetch_california_housing()
return housing
# -*- coding: utf-8 -*-
"""
Created on Thu Sep 26 09:35:56 2019
@author: Morten Sahlertz
"""
from sklearn.datasets.california_housing import fetch_california_housing
import matplotlib.pyplot as plt
import numpy as np
from scipy.stats import norm
cal_housing = fetch_california_housing()
X, y = cal_housing.data, cal_housing.target
names = cal_housing.feature_names
#%% New variable names
median_income = X[:, np.newaxis, 0]
median_house_value = y
#%% Histogram for median income
fig1 = plt.figure()
ax = fig1.add_subplot(111)
ax.hist(median_income, bins=100) # histogram
ax.set_title('Median Income Histogram')
ax.set_xlabel('Median Income')
ax.set_ylabel('Occurences')
#%% Standard deviation, mean and median
standard = np.std(median_income)
print('Spredningen er: {0:.5f}'.format(standard))
def read_data(self):
self.__all = fetch_california_housing()
self.__train_feature, self.__test_feature, self.__train_label, self.__test_label = train_test_split(
self.__all.data, self.__all.target, test_size=0.2, random_state=1)