def test_load_linnerud():
res = load_linnerud()
assert_equal(res.data.shape, (20, 3))
assert_equal(res.target.shape, (20, 3))
assert_equal(len(res.target_names), 3)
assert_true(res.DESCR)
# test return_X_y option
X_y_tuple = load_linnerud(return_X_y=True)
bunch = load_linnerud()
assert_true(isinstance(X_y_tuple, tuple))
assert_array_equal(X_y_tuple[0], bunch.data)
assert_array_equal(X_y_tuple[1], bunch.target)
def test_pls_errors():
d = load_linnerud()
X = d.data
Y = d.target
for clf in [pls_.PLSCanonical(), pls_.PLSRegression(), pls_.PLSSVD()]:
clf.n_components = 4
assert_raise_message(ValueError, "Invalid number of components", clf.fit, X, Y)
def test_convergence_fail():
d = load_linnerud()
X = d.data
Y = d.target
pls_bynipals = pls_.PLSCanonical(n_components=X.shape[1],
max_iter=2, tol=1e-10)
assert_warns(ConvergenceWarning, pls_bynipals.fit, X, Y)
def test_eigsym():
d = load_linnerud()
X = d.data
n = 3
X = dot(X.T, X)
eig = EIGSym(num_comp = n, tolerance = 5e-12)
eig.fit(X)
Xhat = dot(eig.V, dot(eig.D, eig.V.T))
assert_array_almost_equal(X, Xhat, decimal=4, err_msg="EIGSym does not" \
" give the correct reconstruction of the matrix")
[D,V] = np.linalg.eig(X)
# linalg.eig does not return the eigenvalues in order, so need to sort
idx = np.argsort(D, axis=None).tolist()[::-1]
D = D[idx]
V = V[:,idx]
Xhat = dot(V, dot(np.diag(D), V.T))
V, eig.V = direct(V, eig.V, compare = True)
assert_array_almost_equal(V, eig.V, decimal=5, err_msg="EIGSym does not" \
" give the correct eigenvectors")
def test_scale():
d = load_linnerud()
X = d.data
Y = d.target
# causes X[:, -1].std() to be zero
X[:, -1] = 1.0
def test_scale():
d = load_linnerud()
X = d.data
Y = d.target
# causes X[:, -1].std() to be zero
X[:, -1] = 1.0
for clf in [pls.PLSCanonical(), pls.PLSRegression(), pls.CCA(), pls.PLSSVD()]:
clf.set_params(scale=True)
clf.fit(X, Y)
def test_load_linnerud():
res = load_linnerud()
assert_equal(res.data.shape, (20, 3))
assert_equal(res.target.shape, (20, 3))
assert_equal(len(res.target_names), 3)
assert_true(res.DESCR)
assert_true(os.path.exists(res.data_filename))
assert_true(os.path.exists(res.target_filename))
# test return_X_y option
check_return_X_y(res, partial(load_linnerud))
def test_PLSSVD():
# Let's check the PLSSVD doesn't return all possible component but just
# the specified number
d = load_linnerud()
X = d.data
Y = d.target
n_components = 2
for clf in [pls_.PLSSVD, pls_.PLSRegression, pls_.PLSCanonical]:
pls = clf(n_components=n_components)
pls.fit(X, Y)
assert_equal(n_components, pls.y_scores_.shape[1])
def test_univariate_pls_regression():
# Ensure 1d Y is correctly interpreted
d = load_linnerud()
X = d.data
Y = d.target
clf = pls_.PLSRegression()
# Compare 1d to column vector
model1 = clf.fit(X, Y[:, 0]).coef_
model2 = clf.fit(X, Y[:, :1]).coef_
assert_array_almost_equal(model1, model2)
def test_scale_and_stability():
# We test scale=True parameter
# This allows to check numerical stability over platforms as well
d = load_linnerud()
X1 = d.data
Y1 = d.target
# causes X[:, -1].std() to be zero
X1[:, -1] = 1.0
# From bug #2821
# Test with X2, T2 s.t. clf.x_score[:, 1] == 0, clf.y_score[:, 1] == 0
# This test robustness of algorithm when dealing with value close to 0
X2 = np.array([[0., 0., 1.],
[1., 0., 0.],
[2., 2., 2.],
[3., 5., 4.]])
Y2 = np.array([[0.1, -0.2],
[0.9, 1.1],
[6.2, 5.9],
[11.9, 12.3]])
for (X, Y) in [(X1, Y1), (X2, Y2)]:
X_std = X.std(axis=0, ddof=1)
X_std[X_std == 0] = 1
Y_std = Y.std(axis=0, ddof=1)
Y_std[Y_std == 0] = 1
X_s = (X - X.mean(axis=0)) / X_std
Y_s = (Y - Y.mean(axis=0)) / Y_std
for clf in [CCA(), pls_.PLSCanonical(), pls_.PLSRegression(),
pls_.PLSSVD()]:
clf.set_params(scale=True)
X_score, Y_score = clf.fit_transform(X, Y)
clf.set_params(scale=False)
X_s_score, Y_s_score = clf.fit_transform(X_s, Y_s)
assert_array_almost_equal(X_s_score, X_score)
assert_array_almost_equal(Y_s_score, Y_score)
# Scaling should be idempotent
clf.set_params(scale=True)
X_score, Y_score = clf.fit_transform(X_s, Y_s)
assert_array_almost_equal(X_s_score, X_score)
assert_array_almost_equal(Y_s_score, Y_score)
def load_linnerud():
from sklearn.datasets import load_linnerud
linnerud = load_linnerud()
# print(linnerud.DESCR)
print(linnerud.keys())
# print(linnerud.feature_names)
# Chins : 懸垂の回数
# Situps : 腹筋の回数
# Jumps : 跳躍
# print(linnerud.target_names)
# ['Weight', 'Waist', 'Pulse']
X = linnerud.data
y = linnerud.target
return SklearnDataGenerator.shuffle(X, y)
def test_predict_transform_copy():
# check that the "copy" keyword works
d = load_linnerud()
X = d.data
Y = d.target
clf = pls_.PLSCanonical()
X_copy = X.copy()
Y_copy = Y.copy()
clf.fit(X, Y)
# check that results are identical with copy
assert_array_almost_equal(clf.predict(X), clf.predict(X.copy(), copy=False))
assert_array_almost_equal(clf.transform(X), clf.transform(X.copy(), copy=False))
# check also if passing Y
assert_array_almost_equal(clf.transform(X, Y), clf.transform(X.copy(), Y.copy(), copy=False))
# check that copy doesn't destroy
# we do want to check exact equality here
assert_array_equal(X_copy, X)
assert_array_equal(Y_copy, Y)
# also check that mean wasn't zero before (to make sure we didn't touch it)
assert_true(np.all(X.mean(axis=0) != 0))
from sklearn.datasets import load_linnerud
from sklearn.multioutput import MultiOutputRegressor
from sklearn.linear_model import Ridge
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import train_test_split
from MyMultiOutputRegressor.MultiOutputRegressor import *
inputs, outputs = load_linnerud(return_X_y=True)
trainInputs, validationInputs, trainOutputs, validationOutputs = train_test_split(
inputs, outputs, test_size=0.20, random_state=1)
scaler = StandardScaler()
scaler.fit(trainInputs)
trainInputs = scaler.transform(trainInputs)
validationInputs = scaler.transform(validationInputs)
scaler.fit(trainOutputs)
trainOutputs = scaler.transform(trainOutputs)
validationOutputs = scaler.transform(validationOutputs)
print("------------------------sklearn multioutput regressor----------------")
model = MultiOutputRegressor(Ridge(random_state=1)).fit(
trainInputs, trainOutputs)
predictedOutputs = model.predict(validationInputs)
error = mean_squared_error(validationOutputs, predictedOutputs)
print(model.estimators_[0].intercept_, model.estimators_[0].coef_)
print(model.estimators_[1].intercept_, model.estimators_[1].coef_)
print(model.estimators_[2].intercept_, model.estimators_[2].coef_)
print('prediction error', error)
# Import necessary library import numpy as np import pandas as pd # Load the dataset from sklearn.datasets import load_linnerud linnerud_data = load_linnerud() X = linnerud_data.data y = linnerud_data.target from sklearn.tree import DecisionTreeRegressor from sklearn.metrics import mean_squared_error as mse from sklearn.linear_model import LinearRegression # TODO: split the data into training and testing sets, # using the standard settings for train_test_split. # Then, train and test the classifiers with your newly split data instead of X and y. #Solution # Prepare the data as features and labels. features = X labels = y # split the data into training and testing sets from sklearn import cross_validation features_train, features_test, labels_train, labels_test = cross_validation.train_test_split(features, labels, test_size=0.4, random_state=0) # Create decision tree regressor/algorithm object
This example introduces the Regressor object in a multi-target regression task. """ # Author: Alex Wozniakowski <*****@*****.**> import pandas as pd from sklearn.datasets import load_linnerud from sklearn.model_selection import train_test_split from physlearn import Regressor # Load the data from Sklearn bunch = load_linnerud(as_frame=True) # returns a Bunch instance X, y = bunch['data'], bunch['target'] # Split the data, using the default test_size=0.25. # X_train has shape (15, 3), y_train has shape (15, 3) # X_test has shape (5, 3), and y_test has shape (5, 3). # Namely, there are 3 features and 3 single-target regression subtasks. X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42) # Choose the underlying regressor to be the Sklearn # histogram-based gradient boosting regressor. regressor_choice = 'HistGradientBoostingRegressor' # Choose the Sklearn QuantileTransformer as the data preprocessor. # The output distribution is the Gaussian, e.g., 'normal'. # The number of quantiles is the number of examples in y_train,
def load_UCI_dataset(dsIn):
'''Loads a UCI dataset
:param dsIn: the dataset name
:return: A SciKit dataset
'''
from sklearn import datasets
allDSets = {"iris":datasets.load_iris(), "boston":datasets.load_boston(), "diabetes":datasets.load_diabetes(), " linnerud":datasets.load_linnerud()}
dataset = allDSets[dsIn]
return dataset
def test_pls():
d = load_linnerud()
X = d.data
Y = d.target
# 1) Canonical (symmetric) PLS (PLS 2 blocks canonical mode A)
# ===========================================================
# Compare 2 algo.: nipals vs. svd
# ------------------------------
pls_bynipals = pls_.PLSCanonical(n_components=X.shape[1])
pls_bynipals.fit(X, Y)
pls_bysvd = pls_.PLSCanonical(algorithm="svd", n_components=X.shape[1])
pls_bysvd.fit(X, Y)
# check equalities of loading (up to the sign of the second column)
assert_array_almost_equal(
pls_bynipals.x_loadings_,
pls_bysvd.x_loadings_,
decimal=5,
err_msg="nipals and svd implementations lead to different x loadings")
assert_array_almost_equal(
pls_bynipals.y_loadings_,
pls_bysvd.y_loadings_,
decimal=5,
err_msg="nipals and svd implementations lead to different y loadings")
# Check PLS properties (with n_components=X.shape[1])
# ---------------------------------------------------
plsca = pls_.PLSCanonical(n_components=X.shape[1])
plsca.fit(X, Y)
T = plsca.x_scores_
P = plsca.x_loadings_
Wx = plsca.x_weights_
U = plsca.y_scores_
Q = plsca.y_loadings_
Wy = plsca.y_weights_
def check_ortho(M, err_msg):
K = np.dot(M.T, M)
assert_array_almost_equal(K, np.diag(np.diag(K)), err_msg=err_msg)
# Orthogonality of weights
# ~~~~~~~~~~~~~~~~~~~~~~~~
check_ortho(Wx, "x weights are not orthogonal")
check_ortho(Wy, "y weights are not orthogonal")
# Orthogonality of latent scores
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
check_ortho(T, "x scores are not orthogonal")
check_ortho(U, "y scores are not orthogonal")
# Check X = TP' and Y = UQ' (with (p == q) components)
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# center scale X, Y
Xc, Yc, x_mean, y_mean, x_std, y_std =\
pls_._center_scale_xy(X.copy(), Y.copy(), scale=True)
assert_array_almost_equal(Xc, np.dot(T, P.T), err_msg="X != TP'")
assert_array_almost_equal(Yc, np.dot(U, Q.T), err_msg="Y != UQ'")
# Check that rotations on training data lead to scores
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Xr = plsca.transform(X)
assert_array_almost_equal(Xr,
plsca.x_scores_,
err_msg="rotation on X failed")
Xr, Yr = plsca.transform(X, Y)
assert_array_almost_equal(Xr,
plsca.x_scores_,
err_msg="rotation on X failed")
assert_array_almost_equal(Yr,
plsca.y_scores_,
err_msg="rotation on Y failed")
# Check that inverse_transform works
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Xreconstructed = plsca.inverse_transform(Xr)
assert_array_almost_equal(Xreconstructed,
X,
err_msg="inverse_transform failed")
# "Non regression test" on canonical PLS
# --------------------------------------
# The results were checked against the R-package plspm
pls_ca = pls_.PLSCanonical(n_components=X.shape[1])
pls_ca.fit(X, Y)
x_weights = np.array([[-0.61330704, 0.25616119, -0.74715187],
[-0.74697144, 0.11930791, 0.65406368],
[-0.25668686, -0.95924297, -0.11817271]])
# x_weights_sign_flip holds columns of 1 or -1, depending on sign flip
# between R and python
x_weights_sign_flip = pls_ca.x_weights_ / x_weights
x_rotations = np.array([[-0.61330704, 0.41591889, -0.62297525],
[-0.74697144, 0.31388326, 0.77368233],
[-0.25668686, -0.89237972, -0.24121788]])
x_rotations_sign_flip = pls_ca.x_rotations_ / x_rotations
y_weights = np.array([[+0.58989127, 0.7890047, 0.1717553],
[+0.77134053, -0.61351791, 0.16920272],
[-0.23887670, -0.03267062, 0.97050016]])
y_weights_sign_flip = pls_ca.y_weights_ / y_weights
y_rotations = np.array([[+0.58989127, 0.7168115, 0.30665872],
[+0.77134053, -0.70791757, 0.19786539],
[-0.23887670, -0.00343595, 0.94162826]])
y_rotations_sign_flip = pls_ca.y_rotations_ / y_rotations
# x_weights = X.dot(x_rotation)
# Hence R/python sign flip should be the same in x_weight and x_rotation
assert_array_almost_equal(x_rotations_sign_flip, x_weights_sign_flip)
# This test that R / python give the same result up to column
# sign indeterminacy
assert_array_almost_equal(np.abs(x_rotations_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(x_weights_sign_flip), 1, 4)
assert_array_almost_equal(y_rotations_sign_flip, y_weights_sign_flip)
assert_array_almost_equal(np.abs(y_rotations_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(y_weights_sign_flip), 1, 4)
# 2) Regression PLS (PLS2): "Non regression test"
# ===============================================
# The results were checked against the R-packages plspm, misOmics and pls
pls_2 = pls_.PLSRegression(n_components=X.shape[1])
pls_2.fit(X, Y)
x_weights = np.array([[-0.61330704, -0.00443647, 0.78983213],
[-0.74697144, -0.32172099, -0.58183269],
[-0.25668686, 0.94682413, -0.19399983]])
x_weights_sign_flip = pls_2.x_weights_ / x_weights
x_loadings = np.array([[-0.61470416, -0.24574278, 0.78983213],
[-0.65625755, -0.14396183, -0.58183269],
[-0.51733059, 1.00609417, -0.19399983]])
x_loadings_sign_flip = pls_2.x_loadings_ / x_loadings
y_weights = np.array([[+0.32456184, 0.29892183, 0.20316322],
[+0.42439636, 0.61970543, 0.19320542],
[-0.13143144, -0.26348971, -0.17092916]])
y_weights_sign_flip = pls_2.y_weights_ / y_weights
y_loadings = np.array([[+0.32456184, 0.29892183, 0.20316322],
[+0.42439636, 0.61970543, 0.19320542],
[-0.13143144, -0.26348971, -0.17092916]])
y_loadings_sign_flip = pls_2.y_loadings_ / y_loadings
# x_loadings[:, i] = Xi.dot(x_weights[:, i]) \forall i
assert_array_almost_equal(x_loadings_sign_flip, x_weights_sign_flip, 4)
assert_array_almost_equal(np.abs(x_loadings_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(x_weights_sign_flip), 1, 4)
assert_array_almost_equal(y_loadings_sign_flip, y_weights_sign_flip, 4)
assert_array_almost_equal(np.abs(y_loadings_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(y_weights_sign_flip), 1, 4)
# 3) Another non-regression test of Canonical PLS on random dataset
# =================================================================
# The results were checked against the R-package plspm
n = 500
p_noise = 10
q_noise = 5
# 2 latents vars:
rng = check_random_state(11)
l1 = rng.normal(size=n)
l2 = rng.normal(size=n)
latents = np.array([l1, l1, l2, l2]).T
X = latents + rng.normal(size=4 * n).reshape((n, 4))
Y = latents + rng.normal(size=4 * n).reshape((n, 4))
X = np.concatenate((X, rng.normal(size=p_noise * n).reshape(n, p_noise)),
axis=1)
Y = np.concatenate((Y, rng.normal(size=q_noise * n).reshape(n, q_noise)),
axis=1)
pls_ca = pls_.PLSCanonical(n_components=3)
pls_ca.fit(X, Y)
x_weights = np.array([[0.65803719, 0.19197924, 0.21769083],
[0.7009113, 0.13303969, -0.15376699],
[0.13528197, -0.68636408, 0.13856546],
[0.16854574, -0.66788088, -0.12485304],
[-0.03232333, -0.04189855, 0.40690153],
[0.1148816, -0.09643158, 0.1613305],
[0.04792138, -0.02384992, 0.17175319],
[-0.06781, -0.01666137, -0.18556747],
[-0.00266945, -0.00160224, 0.11893098],
[-0.00849528, -0.07706095, 0.1570547],
[-0.00949471, -0.02964127, 0.34657036],
[-0.03572177, 0.0945091, 0.3414855],
[0.05584937, -0.02028961, -0.57682568],
[0.05744254, -0.01482333, -0.17431274]])
x_weights_sign_flip = pls_ca.x_weights_ / x_weights
x_loadings = np.array([[0.65649254, 0.1847647, 0.15270699],
[0.67554234, 0.15237508, -0.09182247],
[0.19219925, -0.67750975, 0.08673128],
[0.2133631, -0.67034809, -0.08835483],
[-0.03178912, -0.06668336, 0.43395268],
[0.15684588, -0.13350241, 0.20578984],
[0.03337736, -0.03807306, 0.09871553],
[-0.06199844, 0.01559854, -0.1881785],
[0.00406146, -0.00587025, 0.16413253],
[-0.00374239, -0.05848466, 0.19140336],
[0.00139214, -0.01033161, 0.32239136],
[-0.05292828, 0.0953533, 0.31916881],
[0.04031924, -0.01961045, -0.65174036],
[0.06172484, -0.06597366, -0.1244497]])
x_loadings_sign_flip = pls_ca.x_loadings_ / x_loadings
y_weights = np.array([[0.66101097, 0.18672553, 0.22826092],
[0.69347861, 0.18463471, -0.23995597],
[0.14462724, -0.66504085, 0.17082434],
[0.22247955, -0.6932605, -0.09832993],
[0.07035859, 0.00714283, 0.67810124],
[0.07765351, -0.0105204, -0.44108074],
[-0.00917056, 0.04322147, 0.10062478],
[-0.01909512, 0.06182718, 0.28830475],
[0.01756709, 0.04797666, 0.32225745]])
y_weights_sign_flip = pls_ca.y_weights_ / y_weights
y_loadings = np.array([[0.68568625, 0.1674376, 0.0969508],
[0.68782064, 0.20375837, -0.1164448],
[0.11712173, -0.68046903, 0.12001505],
[0.17860457, -0.6798319, -0.05089681],
[0.06265739, -0.0277703, 0.74729584],
[0.0914178, 0.00403751, -0.5135078],
[-0.02196918, -0.01377169, 0.09564505],
[-0.03288952, 0.09039729, 0.31858973],
[0.04287624, 0.05254676, 0.27836841]])
y_loadings_sign_flip = pls_ca.y_loadings_ / y_loadings
assert_array_almost_equal(x_loadings_sign_flip, x_weights_sign_flip, 4)
assert_array_almost_equal(np.abs(x_weights_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(x_loadings_sign_flip), 1, 4)
assert_array_almost_equal(y_loadings_sign_flip, y_weights_sign_flip, 4)
assert_array_almost_equal(np.abs(y_weights_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(y_loadings_sign_flip), 1, 4)
# Orthogonality of weights
# ~~~~~~~~~~~~~~~~~~~~~~~~
check_ortho(pls_ca.x_weights_, "x weights are not orthogonal")
check_ortho(pls_ca.y_weights_, "y weights are not orthogonal")
# Orthogonality of latent scores
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
check_ortho(pls_ca.x_scores_, "x scores are not orthogonal")
check_ortho(pls_ca.y_scores_, "y scores are not orthogonal")
# 4) Another "Non regression test" of PLS Regression (PLS2):
# Checking behavior when the first column of Y is constant
# ===============================================
# The results were compared against a modified version of plsreg2
# from the R-package plsdepot
X = d.data
Y = d.target
Y[:, 0] = 1
pls_2 = pls_.PLSRegression(n_components=X.shape[1])
pls_2.fit(X, Y)
x_weights = np.array([[-0.6273573, 0.007081799, 0.7786994],
[-0.7493417, -0.277612681, -0.6011807],
[-0.2119194, 0.960666981, -0.1794690]])
x_weights_sign_flip = pls_2.x_weights_ / x_weights
x_loadings = np.array([[-0.6273512, -0.22464538, 0.7786994],
[-0.6643156, -0.09871193, -0.6011807],
[-0.5125877, 1.01407380, -0.1794690]])
x_loadings_sign_flip = pls_2.x_loadings_ / x_loadings
y_loadings = np.array([[0.0000000, 0.0000000, 0.0000000],
[0.4357300, 0.5828479, 0.2174802],
[-0.1353739, -0.2486423, -0.1810386]])
# R/python sign flip should be the same in x_weight and x_rotation
assert_array_almost_equal(x_loadings_sign_flip, x_weights_sign_flip, 4)
# This test that R / python give the same result up to column
# sign indeterminacy
assert_array_almost_equal(np.abs(x_loadings_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(x_weights_sign_flip), 1, 4)
# For the PLSRegression with default parameters, it holds that
# y_loadings==y_weights. In this case we only test that R/python
# give the same result for the y_loadings irrespective of the sign
assert_array_almost_equal(np.abs(pls_2.y_loadings_), np.abs(y_loadings), 4)
######################### import stuff ##########################
import numpy as np
import pandas as pd
import tensorflow as tf
from sklearn.datasets import load_linnerud
from sklearn.model_selection import train_test_split
######################## prepare the data ########################
X, y = load_linnerud(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.33,
random_state=5)
######################## set learning variables ##################
learning_rate = 0.0005
epochs = 2000
batch_size = 3
######################## set some variables #######################
x = tf.placeholder(tf.float32, [None, 3], name='x') # 3 features
y = tf.placeholder(tf.float32, [None, 3], name='y') # 3 outputs
# hidden layer 1
W1 = tf.Variable(tf.truncated_normal([3, 10], stddev=0.03), name='W1')
b1 = tf.Variable(tf.truncated_normal([10]), name='b1')
# hidden layer 2
W2 = tf.Variable(tf.truncated_normal([10, 3], stddev=0.03), name='W2')
b2 = tf.Variable(tf.truncated_normal([3]), name='b2')
def create_linnerud():
linnerud_data = datasets.load_linnerud()
assert False
assert sm.var_test_scaler.mean_.all() == np.array([[7.8, 154.8,
104.4]]).all()
assert sm.var_test_scaler.var_.all() == np.array(
[[34.16, 5246.16, 6053.44]]).all()
assert sm.obj_train_scaler.mean_.all() == np.array(
[[173.06666667, 34.66666667, 56.53333333]]).all()
assert sm.obj_train_scaler.var_.all() == np.array(
[[341.79555556, 4.35555556, 58.38222222]]).all()
assert sm.obj_test_scaler.mean_.all() == np.array([[195.2, 37.6,
54.8]]).all()
assert sm.obj_test_scaler.var_.all() == np.array([[923.76, 19.44,
20.16]]).all()
model = tm.Surrogate_Models()
variables, objectives = datasets.load_linnerud(return_X_y=True)
model.random = 57757
model.update_database(np.ndarray.tolist(variables),
np.ndarray.tolist(objectives))
model._initialize_models()
def test_initialize_models():
models = model.models
assert 'lr' in models
assert 'pr' in models
assert 'mars' in models
assert 'gpr' in models
assert 'ann' in models
assert 'rf' in models
# [ 10.73412075 166.87684314 85.9018666 174.46486234 34.77098762 # 56.57285616] # [ 18.69314353 299.06132114 182.60275097 148.83514259 30.87234812 # 59.50363423] # [ 7.65798496 115.78798285 48.52729701 184.37066362 36.2777988 # 55.4401202 ] # [ 13.25814681 208.79619397 116.56838932 166.33696994 33.5346213 # 57.50228687] # [ 13.26989716 208.9913453 116.71115423 166.29913135 33.52886552 # 57.50661375] # [ 4.69419072 66.56490544 12.51765966 193.91470161 37.7295807 # 54.34875215] # [ 5.34592844 77.38904966 20.43617123 191.8159697 37.41033417 # 54.58874375] # [ 13.13301791 206.71803705 115.04809272 166.7399112 33.59591431 # 57.45621023] # [ 4.9236322 70.37549919 15.30533784 193.175852 37.61719133 # 54.43324017] # [ 13.10738592 206.29233749 114.73666792 166.8224516 33.60846986 # 57.44677168] # [ 12.73830285 200.16255828 110.25236629 168.01097635 33.78926113 # 57.31086296] # [ 7.62722272 115.27707959 48.15354059 184.46972448 36.29286734 # 55.42879251]] # 5) # 0.78 ll = load_linnerud() print(ll.DESCR)
def scikitAlgorithms_UCIDataset(input_dict):
from sklearn import datasets
allDSets = {"iris":datasets.load_iris(), "boston":datasets.load_boston(), "diabetes":datasets.load_diabetes(), " linnerud":datasets.load_linnerud()}
dataset = allDSets[input_dict['dsIn']]
output_dict = {}
output_dict['dtsOut'] = dataset#(dataset.data, dataset.target)
return output_dict
def run_4(feature_to_plot):
# Generate some 2D coefficients with sine waves with random frequency and phase
from sklearn.datasets import load_linnerud
linnerud = load_linnerud()
"""
print(linnerud.feature_names)
print(linnerud.data)
print(linnerud.target_names)
print(linnerud.target)
"""
X, Y = linnerud.data, linnerud.target
# [print(y) for y in Y.T]
coef_ridge_ = np.array([Ridge(alpha=0.5).fit(X, y).coef_ for y in Y.T])
coef_lasso_ = np.array([Lasso(alpha=0.5).fit(X, y).coef_ for y in Y.T])
coef_multi_task_lasso_ = MultiTaskLasso(alpha=1.).fit(X, Y).coef_
coef_low_ranked_ = low_ranked_regression(X, Y, 3)
# #############################################################################
# Plot support and time series
fig = plt.figure(figsize=(8, 5))
plt.subplot(1, 2, 1)
plt.spy(coef_lasso_)
plt.xlabel('Feature')
plt.ylabel('Time (or Task)')
plt.text(10, 5, 'Lasso')
plt.subplot(1, 2, 2)
plt.spy(coef_multi_task_lasso_)
plt.xlabel('Feature')
plt.ylabel('Time (or Task)')
plt.text(10, 5, 'MultiTaskLasso')
fig.suptitle('Coefficient non-zero location')
plt.tight_layout()
plt.figure()
lw = 1
"""
plt.plot(Y[:, feature_to_plot], color='seagreen', linewidth=lw,
label='Ground truth')
"""
plt.plot(coef_lasso_[:, feature_to_plot],
color='cornflowerblue',
linewidth=lw,
label='Lasso')
plt.plot(coef_ridge_[:, feature_to_plot],
color='red',
linewidth=lw,
label='Ridge')
plt.plot(coef_low_ranked_[:, feature_to_plot],
color='magenta',
linewidth=lw,
label='LowRanked')
plt.plot(coef_multi_task_lasso_[:, feature_to_plot],
color='gold',
linewidth=lw,
label='MultiTaskLasso')
plt.legend(loc='upper center')
plt.axis('tight')
plt.ylim([-1.1, 1.1])
plt.tight_layout()
plt.show()
print()
print('--------------------------乳腺癌数据集------------------------')
from sklearn.datasets import load_breast_cancer
breast_cancer = load_breast_cancer()
print('简单经典的用于二分类任务的数据集')
print('数据属性', breast_cancer.keys())
print()
print('其他数据集')
from sklearn.datasets import load_boston
from sklearn.datasets import load_diabetes
from sklearn.datasets import load_digits
from sklearn.datasets import load_linnerud
from sklearn.datasets import load_wine
print('波士顿房价数据集load-boston是经典的用于回归任务的数据集')
print('波士顿房价数据集的数据属性为', load_boston().keys())
print('糖尿病数据集load-diabetes是经典的用于回归任务的数据集')
print('手写数字数据集load_digits适用于多分类任务的数据集')
print('体能训练数据集load-linnerud是经典的用于多变量回归任务的数据集，其内部包含两个小数据集'
'：Excise是对三个训练变量（引体向上、仰卧起坐、立定跳远）的20次观测；physiological是对'
'三个生理学变量（体重、腰围、脉搏）的20次观测')
print(load_linnerud().keys())
print(load_linnerud().target)
print(load_linnerud().target_names)
print(load_linnerud().feature_names)
print('葡萄酒数据集load-wine包括了3中酒中13中不同成分的数量，共178个样本，对应三种葡萄酒')
print(load_wine().target_names)
print(load_wine().keys())
print(load_wine().feature_names)
def experimentVariables(projectName):
'''
This function returns all the variables necessary to start a experiment including:
name of the experiment
datasets locations
variables to report from the experiment
what to report from the experiment
'''
computerName=os.environ.get('COMPUTERNAME')
if projectName== 'unlabeledModelS':
if computerName=='JULIAN':
from sklearn.datasets import load_boston, load_iris, load_diabetes, load_digits, load_linnerud
datasets={'boston':load_boston(),'iris':load_iris(),'diabetes':load_diabetes(),'digits':load_digits(),'linnerud':load_linnerud()}
print('working at JULIAN@CMU')
dataset='digits'
numTests=50
experimentName='One'
agmntlvl=0
description='here the description of this experiment'
data=datasets[dataset]['data']
labels=datasets[dataset]['target']
verbose=0
plots=False
signal2plot='f1_score_mv_predval_agmnt'
# signal2plot='f1_score_val_predval_agmnt'
#The next are variables that store the outcomes from the
#experiment
variables=\
'spear=[]\n'
return {'dataset':dataset,'numTests':numTests,'experimentName':experimentName,\
'description':description,'agmntlvl':agmntlvl,'variables':variables,'data':data,\
'labels':labels,'verbose':verbose,'plots':plots,'signal2plot':signal2plot}
else:
print('Variables not defined for Julian@Laptop')
def loadRegSample(self):
''' load regression sample dataset '''
self.data = load_linnerud()
logger.info(self.data.DESCR)
def test_predictions():
d = load_linnerud()
X = d.data
Y = d.target
tol = 5e-12
miter = 1000
num_comp = 2
Xorig = X.copy()
Yorig = Y.copy()
# SSY = np.sum(Yorig**2)
# center = True
scale = False
pls1 = PLSRegression(n_components = num_comp, scale = scale,
tol = tol, max_iter = miter, copy = True)
pls1.fit(Xorig, Yorig)
Yhat1 = pls1.predict(Xorig)
SSYdiff1 = np.sum((Yorig-Yhat1)**2)
# print "PLSRegression: R2Yhat = %.4f" % (1 - (SSYdiff1 / SSY))
# Compare PLSR and sklearn.PLSRegression
pls3 = PLSR(num_comp = num_comp, center = True, scale = scale,
tolerance = tol, max_iter = miter)
pls3.fit(X, Y)
Yhat3 = pls3.predict(X)
assert_array_almost_equal(Yhat1, Yhat3, decimal = 5,
err_msg = "PLSR gives wrong prediction")
SSYdiff3 = np.sum((Yorig-Yhat3)**2)
# print "PLSR : R2Yhat = %.4f" % (1 - (SSYdiff3 / SSY))
assert abs(SSYdiff1 - SSYdiff3) < 0.00005
pls2 = PLSCanonical(n_components = num_comp, scale = scale,
tol = tol, max_iter = miter, copy = True)
pls2.fit(Xorig, Yorig)
Yhat2 = pls2.predict(Xorig)
SSYdiff2 = np.sum((Yorig-Yhat2)**2)
# print "PLSCanonical : R2Yhat = %.4f" % (1 - (SSYdiff2 / SSY))
# Compare PLSC and sklearn.PLSCanonical
pls4 = PLSC(num_comp = num_comp, center = True, scale = scale,
tolerance = tol, max_iter = miter)
pls4.fit(X, Y)
Yhat4 = pls4.predict(X)
SSYdiff4 = np.sum((Yorig-Yhat4)**2)
# print "PLSC : R2Yhat = %.4f" % (1 - (SSYdiff4 / SSY))
# Compare O2PLS and sklearn.PLSCanonical
pls5 = O2PLS(num_comp = [num_comp, 1, 0], center = True, scale = scale,
tolerance = tol, max_iter = miter)
pls5.fit(X, Y)
Yhat5 = pls5.predict(X)
SSYdiff5 = np.sum((Yorig-Yhat5)**2)
# print "O2PLS : R2Yhat = %.4f" % (1 - (SSYdiff5 / SSY))
assert abs(SSYdiff2 - SSYdiff4) < 0.00005
assert SSYdiff2 > SSYdiff5
def test_update_database():
sm = tm.Surrogate_Models()
variables, objectives = datasets.load_linnerud(return_X_y=True)
sm.random = 57757
sm.update_database(np.ndarray.tolist(variables),
np.ndarray.tolist(objectives))
ind_var_given = [[
11,
230,
80,
], [
6,
70,
31,
], [
2,
110,
43,
], [
14,
215,
105,
], [
15,
225,
73,
], [
4,
60,
25,
], [
12,
105,
37,
], [
12,
101,
101,
], [
13,
210,
115,
], [
13,
155,
58,
], [
2,
110,
60,
], [
15,
200,
40,
], [
6,
125,
40,
], [
8,
101,
38,
], [
17,
120,
38,
]]
obj_var_given = [[
157,
32,
52,
], [
193,
36,
46,
], [
138,
33,
68,
], [
154,
34,
64,
], [
156,
33,
54,
], [
176,
37,
54,
], [
162,
35,
62,
], [
193,
38,
58,
], [
166,
33,
52,
], [
189,
35,
46,
], [
189,
37,
52,
], [
176,
31,
74,
], [
167,
34,
60,
], [
211,
38,
56,
], [
169,
34,
50,
]]
np.testing.assert_array_equal(sm.var_train, ind_var_given)
np.testing.assert_array_equal(sm.obj_train, obj_var_given)
assert len(sm.var_test) == 5
assert len(sm.obj_test) == 5
sm.update_database([
[
12,
250,
85,
],
[
12,
250,
85,
],
], [[
165,
33,
57,
], [
165,
33,
57,
]])
assert len(sm.var_train) == 16
assert len(sm.obj_train) == 16
assert len(sm.var_test) == 6
assert len(sm.obj_test) == 6
import numpy as np
import pandas as pd
# Load the dataset
from sklearn.datasets import load_linnerud
linnerud_data = load_linnerud()
X = linnerud_data.data
y = linnerud_data.target
from sklearn.tree import DecisionTreeRegressor
from sklearn.metrics import mean_absolute_error as mae
from sklearn.linear_model import LinearRegression
from sklearn import cross_validation
from sklearn.metrics import mean_squared_error as mse
x_train, x_test, y_train, y_test = cross_validation.train_test_split(X, y)
reg1 = DecisionTreeRegressor()
reg1.fit(x_train, y_train)
mean_absolute_error_tree = mae(reg1.predict(x_test), y_test)
mean_squared_error_tree = mse(reg1.predict(x_test), y_test)
print "Decision Tree mean absolute error: {:.2f}".format(
mean_absolute_error_tree)
print "Decision Tree mean absolute error: {:.2f}".format(
mean_squared_error_tree)
reg2 = LinearRegression()
reg2.fit(x_train, y_train)
mean_absolute_error_linear = mae(reg2.predict(x_test), y_test)
mean_squared_error_linear = mse(reg2.predict(x_test), y_test)
x_data = np.zeros([20,2])
x_data[:,0] = 1
x_data[:,1] = x
y_data = y
y_data = np.expand_dims(y_data,axis=1)
# compute the weights
W = np.dot(np.dot(inv((np.dot(x_data.T,x_data))),x_data.T),y_data)
return W
# -- Get data
data_set = load_linnerud()
raw_data = data_set.data # Chins, Situps, Jumps
features_names = data_set.feature_names
target_data = data_set.target # Weight, Waist, Pulse
target_names = data_set.target_names
fig, axis = plt.subplots(3, 3)
fig.set_size_inches(20,25)
for i in range(len(target_names)):
x_temp = target_data[:,i]
for j in range(len(features_names)):
def test_linnerud_data():
X, y = load_linnerud(return_X_y=True)
assert apply_toy_on(X, y) > -3000
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets, linear_model
from sklearn.metrics import mean_squared_error, r2_score
from mpl_toolkits.mplot3d import Axes3D
lin = datasets.load_linnerud()
lin_features = lin.feature_names
X = lin.data[:, np.newaxis, 2]
X_train = X[:-15]
X_test = X[-15:]
y_train = lin.target[:-15]
y_test = lin.target[-15:]
regression = linear_model.LinearRegression()
# training
regression.fit(X_train, y_train)
# prediction
y_pred = regression.predict(X_test)
print('Coeficients: \n', regression.coef_)
print("Mean squared error: \n %.2f" % mean_squared_error(y_test, y_pred))
print('Variance Score: \n %.2f' %r2_score(y_test, y_pred))
#exec(open('.\\trees\\sklearn\\datasets.py').read())
import subprocess as sp
from sklearn.datasets import load_boston
from sklearn.datasets import load_iris
from sklearn.datasets import load_diabetes
from sklearn.datasets import load_digits
from sklearn.datasets import load_linnerud
from sklearn.datasets import load_wine
from sklearn.datasets import load_breast_cancer
if __name__ == '__main__':
sp.call('cls', shell=True)
# load the iris dataset
ds = dict()
ds['iris'] = load_iris()
ds['boston'] = load_boston()
ds['iris'] = load_iris()
ds['diabetes'] = load_diabetes()
ds['digits'] = load_digits()
ds['linnerud'] = load_linnerud()
ds['wine'] = load_wine()
ds['breastcancer'] = load_breast_cancer()
# print the keys of every dataset
for key in ds:
print(key)
for key2 in ds[key]:
print('{0}{1}'.format(' ', key2))
import numpy as np
from numpy.testing import assert_array_almost_equal
from sklearn.datasets import load_linnerud
from sklearn import pls
d = load_linnerud()
X = d.data
Y = d.target
def test_pls():
n_components = 2
# 1) Canonical (symetric) PLS (PLS 2 blocks canonical mode A)
# ===========================================================
# Compare 2 algo.: nipals vs. svd
# ------------------------------
pls_bynipals = pls.PLSCanonical(n_components=n_components)
pls_bynipals.fit(X, Y)
pls_bysvd = pls.PLSCanonical(algorithm="svd", n_components=n_components)
pls_bysvd.fit(X, Y)
# check that the loading vectors are highly correlated
assert_array_almost_equal(
[
np.abs(np.corrcoef(pls_bynipals.x_loadings_[:, k], pls_bysvd.x_loadings_[:, k])[1, 0])
for k in xrange(n_components)
],
np.ones(n_components),
err_msg="nipals and svd implementation lead to different x loadings",
)
assert_array_almost_equal(
def load_multi_data(self):
x, y = datasets.load_linnerud(return_X_y=True)
self.__inputs = x.tolist()
self.__outputs = y.tolist()
#solution_dsci_chapter_02_diabetes.py
"""Data from scikit-learn's traing data, and are based on
clinical data available here:
http://www4.stat.ncsu.edu/~boos/var.select/diabetes.html
Documentation for this
and lots of other machine learning sets can be found here:
http://scikit-learn.org/stable/datasets/index.html
"""
import sklearn.datasets as ds
import pandas as pd
#everything=ds.load_diabetes()
everything=ds.load_linnerud()
#build DataFrame objects with contents of the data set
eser=pd.DataFrame(everything['data'], columns=everything['feature_names'])
pser=pd.DataFrame(everything['target'], columns=everything['target_names'])
#combine the two series a column at a time
for c in pser.columns:
eser.assign(c=pser[c], inplace=True) #alternative: eser[c]=pser[c]
x=1
#create an "exercise index"
eser.assign(eindex=eser['Chins'] * 3 +
eser["Situps"] * 2 +
eser["Jumps"])
#convert the Weight to kilos (2.2 lb = 1 kg)
eser['Weight']=eser['Weight']/2.2
def create_linnerud():
linnerud_data = datasets.load_linnerud()
assert False
# This tutorial is more about understanding datasets in scikit
# Toy Dataset
# By default scikit comes with preloaded data set for practicing machine leaning algorithms.
from sklearn import datasets
iris_data = datasets.load_iris() # Classification
wine_data = datasets.load_wine() # Classification
cancer_data = datasets.load_breast_cancer() # Classification
diabetes_data = datasets.load_diabetes() # Regression
boston_data = datasets.load_boston() # Regression
linnerud_data = datasets.load_linnerud() # Multivariate Regression
# Accessing data
# By default datasets return Bunch - Dictionary like object.
# Bunch has target variable (Y) and feature variable (X).
X = iris_data.get("data")
Y = iris_data.get("target")
feature_names = iris_data.get("feature_names")
target_names = iris_data.get("target_names") # nothing but lable name
X = diabetes_data.get("data")
Y = diabetes_data.get("target")
feature_names = diabetes_data.get("feature_names")
# for regression problems there is no target_names
# for more details about dataset visit
# http://scikit-learn.org/stable/datasets/index.html#datasets
# coding=utf-8
from sklearn import datasets
import numpy as np
import matplotlib.pyplot as plt
d1 = datasets.load_iris() #
d2 = datasets.load_breast_cancer() #乳腺癌数据
d3 = datasets.load_digits() #手写数字
d4 = datasets.load_boston() #波士顿房价
d5 = datasets.load_linnerud() #体能数据集
print(d3.keys())
samples,features = d3.data.shape
print(samples,features)
print(d3.images.shape)
#print(d1.data)
#print(d1.target)
print(d3.target_names)
print(np.bincount(d1.target))
x_index = 3
colors = ['blue','red','green']
'''
for label,color in zip(range(len(d1.target_names)),colors):
plt.hist(d1.data[d1.target==label,x_index],label=d1.target_names[label],color=color) #直方图
def test_pls():
d = load_linnerud()
X = d.data
Y = d.target
# 1) Canonical (symetric) PLS (PLS 2 blocks canonical mode A)
# ===========================================================
# Compare 2 algo.: nipals vs. svd
# ------------------------------
pls_bynipals = pls.PLSCanonical(n_components=X.shape[1])
pls_bynipals.fit(X, Y)
pls_bysvd = pls.PLSCanonical(algorithm="svd", n_components=X.shape[1])
pls_bysvd.fit(X, Y)
# check equalities of loading (up to the sign of the second column)
assert_array_almost_equal(
pls_bynipals.x_loadings_,
np.multiply(pls_bysvd.x_loadings_, np.array([1, -1, 1])), decimal=5,
err_msg="nipals and svd implementation lead to different x loadings")
assert_array_almost_equal(
pls_bynipals.y_loadings_,
np.multiply(pls_bysvd.y_loadings_, np.array([1, -1, 1])), decimal=5,
err_msg="nipals and svd implementation lead to different y loadings")
# Check PLS properties (with n_components=X.shape[1])
# ---------------------------------------------------
plsca = pls.PLSCanonical(n_components=X.shape[1])
plsca.fit(X, Y)
T = plsca.x_scores_
P = plsca.x_loadings_
Wx = plsca.x_weights_
U = plsca.y_scores_
Q = plsca.y_loadings_
Wy = plsca.y_weights_
def check_ortho(M, err_msg):
K = np.dot(M.T, M)
assert_array_almost_equal(K, np.diag(np.diag(K)), err_msg=err_msg)
# Orthogonality of weights
# ~~~~~~~~~~~~~~~~~~~~~~~~
check_ortho(Wx, "x weights are not orthogonal")
check_ortho(Wy, "y weights are not orthogonal")
# Orthogonality of latent scores
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
check_ortho(T, "x scores are not orthogonal")
check_ortho(U, "y scores are not orthogonal")
# Check X = TP' and Y = UQ' (with (p == q) components)
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# center scale X, Y
Xc, Yc, x_mean, y_mean, x_std, y_std =\
pls._center_scale_xy(X.copy(), Y.copy(), scale=True)
assert_array_almost_equal(Xc, np.dot(T, P.T), err_msg="X != TP'")
assert_array_almost_equal(Yc, np.dot(U, Q.T), err_msg="Y != UQ'")
# Check that rotations on training data lead to scores
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Xr = plsca.transform(X)
assert_array_almost_equal(Xr, plsca.x_scores_,
err_msg="rotation on X failed")
Xr, Yr = plsca.transform(X, Y)
assert_array_almost_equal(Xr, plsca.x_scores_,
err_msg="rotation on X failed")
assert_array_almost_equal(Yr, plsca.y_scores_,
err_msg="rotation on Y failed")
# "Non regression test" on canonical PLS
# --------------------------------------
# The results were checked against the R-package plspm
pls_ca = pls.PLSCanonical(n_components=X.shape[1])
pls_ca.fit(X, Y)
x_weights = np.array(
[[-0.61330704, 0.25616119, -0.74715187],
[-0.74697144, 0.11930791, 0.65406368],
[-0.25668686, -0.95924297, -0.11817271]])
assert_array_almost_equal(pls_ca.x_weights_, x_weights)
x_rotations = np.array(
[[-0.61330704, 0.41591889, -0.62297525],
[-0.74697144, 0.31388326, 0.77368233],
[-0.25668686, -0.89237972, -0.24121788]])
assert_array_almost_equal(pls_ca.x_rotations_, x_rotations)
y_weights = np.array(
[[+0.58989127, 0.7890047, 0.1717553],
[+0.77134053, -0.61351791, 0.16920272],
[-0.23887670, -0.03267062, 0.97050016]])
assert_array_almost_equal(pls_ca.y_weights_, y_weights)
y_rotations = np.array(
[[+0.58989127, 0.7168115, 0.30665872],
[+0.77134053, -0.70791757, 0.19786539],
[-0.23887670, -0.00343595, 0.94162826]])
assert_array_almost_equal(pls_ca.y_rotations_, y_rotations)
# 2) Regression PLS (PLS2): "Non regression test"
# ===============================================
# The results were checked against the R-packages plspm, misOmics and pls
pls_2 = pls.PLSRegression(n_components=X.shape[1])
pls_2.fit(X, Y)
x_weights = np.array(
[[-0.61330704, -0.00443647, 0.78983213],
[-0.74697144, -0.32172099, -0.58183269],
[-0.25668686, 0.94682413, -0.19399983]])
assert_array_almost_equal(pls_2.x_weights_, x_weights)
x_loadings = np.array(
[[-0.61470416, -0.24574278, 0.78983213],
[-0.65625755, -0.14396183, -0.58183269],
[-0.51733059, 1.00609417, -0.19399983]])
assert_array_almost_equal(pls_2.x_loadings_, x_loadings)
y_weights = np.array(
[[+0.32456184, 0.29892183, 0.20316322],
[+0.42439636, 0.61970543, 0.19320542],
[-0.13143144, -0.26348971, -0.17092916]])
assert_array_almost_equal(pls_2.y_weights_, y_weights)
y_loadings = np.array(
[[+0.32456184, 0.29892183, 0.20316322],
[+0.42439636, 0.61970543, 0.19320542],
[-0.13143144, -0.26348971, -0.17092916]])
assert_array_almost_equal(pls_2.y_loadings_, y_loadings)
# 3) Another non-regression test of Canonical PLS on random dataset
# =================================================================
# The results were checked against the R-package plspm
n = 500
p_noise = 10
q_noise = 5
# 2 latents vars:
np.random.seed(11)
l1 = np.random.normal(size=n)
l2 = np.random.normal(size=n)
latents = np.array([l1, l1, l2, l2]).T
X = latents + np.random.normal(size=4 * n).reshape((n, 4))
Y = latents + np.random.normal(size=4 * n).reshape((n, 4))
X = np.concatenate(
(X, np.random.normal(size=p_noise * n).reshape(n, p_noise)), axis=1)
Y = np.concatenate(
(Y, np.random.normal(size=q_noise * n).reshape(n, q_noise)), axis=1)
np.random.seed(None)
pls_ca = pls.PLSCanonical(n_components=3)
pls_ca.fit(X, Y)
x_weights = np.array(
[[0.65803719, 0.19197924, 0.21769083],
[0.7009113, 0.13303969, -0.15376699],
[0.13528197, -0.68636408, 0.13856546],
[0.16854574, -0.66788088, -0.12485304],
[-0.03232333, -0.04189855, 0.40690153],
[0.1148816, -0.09643158, 0.1613305],
[0.04792138, -0.02384992, 0.17175319],
[-0.06781, -0.01666137, -0.18556747],
[-0.00266945, -0.00160224, 0.11893098],
[-0.00849528, -0.07706095, 0.1570547],
[-0.00949471, -0.02964127, 0.34657036],
[-0.03572177, 0.0945091, 0.3414855],
[0.05584937, -0.02028961, -0.57682568],
[0.05744254, -0.01482333, -0.17431274]])
assert_array_almost_equal(pls_ca.x_weights_, x_weights)
x_loadings = np.array(
[[0.65649254, 0.1847647, 0.15270699],
[0.67554234, 0.15237508, -0.09182247],
[0.19219925, -0.67750975, 0.08673128],
[0.2133631, -0.67034809, -0.08835483],
[-0.03178912, -0.06668336, 0.43395268],
[0.15684588, -0.13350241, 0.20578984],
[0.03337736, -0.03807306, 0.09871553],
[-0.06199844, 0.01559854, -0.1881785],
[0.00406146, -0.00587025, 0.16413253],
[-0.00374239, -0.05848466, 0.19140336],
[0.00139214, -0.01033161, 0.32239136],
[-0.05292828, 0.0953533, 0.31916881],
[0.04031924, -0.01961045, -0.65174036],
[0.06172484, -0.06597366, -0.1244497]])
assert_array_almost_equal(pls_ca.x_loadings_, x_loadings)
y_weights = np.array(
[[0.66101097, 0.18672553, 0.22826092],
[0.69347861, 0.18463471, -0.23995597],
[0.14462724, -0.66504085, 0.17082434],
[0.22247955, -0.6932605, -0.09832993],
[0.07035859, 0.00714283, 0.67810124],
[0.07765351, -0.0105204, -0.44108074],
[-0.00917056, 0.04322147, 0.10062478],
[-0.01909512, 0.06182718, 0.28830475],
[0.01756709, 0.04797666, 0.32225745]])
assert_array_almost_equal(pls_ca.y_weights_, y_weights)
y_loadings = np.array(
[[0.68568625, 0.1674376, 0.0969508],
[0.68782064, 0.20375837, -0.1164448],
[0.11712173, -0.68046903, 0.12001505],
[0.17860457, -0.6798319, -0.05089681],
[0.06265739, -0.0277703, 0.74729584],
[0.0914178, 0.00403751, -0.5135078],
[-0.02196918, -0.01377169, 0.09564505],
[-0.03288952, 0.09039729, 0.31858973],
[0.04287624, 0.05254676, 0.27836841]])
assert_array_almost_equal(pls_ca.y_loadings_, y_loadings)
# Orthogonality of weights
# ~~~~~~~~~~~~~~~~~~~~~~~~
check_ortho(pls_ca.x_weights_, "x weights are not orthogonal")
check_ortho(pls_ca.y_weights_, "y weights are not orthogonal")
# Orthogonality of latent scores
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
check_ortho(pls_ca.x_scores_, "x scores are not orthogonal")
check_ortho(pls_ca.y_scores_, "y scores are not orthogonal")
def test_pls():
d = load_linnerud()
X = d.data
Y = d.target
# 1) Canonical (symmetric) PLS (PLS 2 blocks canonical mode A)
# ===========================================================
# Compare 2 algo.: nipals vs. svd
# ------------------------------
pls_bynipals = pls_.PLSCanonical(n_components=X.shape[1])
pls_bynipals.fit(X, Y)
pls_bysvd = pls_.PLSCanonical(algorithm="svd", n_components=X.shape[1])
pls_bysvd.fit(X, Y)
# check equalities of loading (up to the sign of the second column)
assert_array_almost_equal(
pls_bynipals.x_loadings_,
pls_bysvd.x_loadings_, decimal=5,
err_msg="nipals and svd implementations lead to different x loadings")
assert_array_almost_equal(
pls_bynipals.y_loadings_,
pls_bysvd.y_loadings_, decimal=5,
err_msg="nipals and svd implementations lead to different y loadings")
# Check PLS properties (with n_components=X.shape[1])
# ---------------------------------------------------
plsca = pls_.PLSCanonical(n_components=X.shape[1])
plsca.fit(X, Y)
T = plsca.x_scores_
P = plsca.x_loadings_
Wx = plsca.x_weights_
U = plsca.y_scores_
Q = plsca.y_loadings_
Wy = plsca.y_weights_
def check_ortho(M, err_msg):
K = np.dot(M.T, M)
assert_array_almost_equal(K, np.diag(np.diag(K)), err_msg=err_msg)
# Orthogonality of weights
# ~~~~~~~~~~~~~~~~~~~~~~~~
check_ortho(Wx, "x weights are not orthogonal")
check_ortho(Wy, "y weights are not orthogonal")
# Orthogonality of latent scores
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
check_ortho(T, "x scores are not orthogonal")
check_ortho(U, "y scores are not orthogonal")
# Check X = TP' and Y = UQ' (with (p == q) components)
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# center scale X, Y
Xc, Yc, x_mean, y_mean, x_std, y_std =\
pls_._center_scale_xy(X.copy(), Y.copy(), scale=True)
assert_array_almost_equal(Xc, np.dot(T, P.T), err_msg="X != TP'")
assert_array_almost_equal(Yc, np.dot(U, Q.T), err_msg="Y != UQ'")
# Check that rotations on training data lead to scores
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Xr = plsca.transform(X)
assert_array_almost_equal(Xr, plsca.x_scores_,
err_msg="rotation on X failed")
Xr, Yr = plsca.transform(X, Y)
assert_array_almost_equal(Xr, plsca.x_scores_,
err_msg="rotation on X failed")
assert_array_almost_equal(Yr, plsca.y_scores_,
err_msg="rotation on Y failed")
# "Non regression test" on canonical PLS
# --------------------------------------
# The results were checked against the R-package plspm
pls_ca = pls_.PLSCanonical(n_components=X.shape[1])
pls_ca.fit(X, Y)
x_weights = np.array(
[[-0.61330704, 0.25616119, -0.74715187],
[-0.74697144, 0.11930791, 0.65406368],
[-0.25668686, -0.95924297, -0.11817271]])
# x_weights_sign_flip holds columns of 1 or -1, depending on sign flip
# between R and python
x_weights_sign_flip = pls_ca.x_weights_ / x_weights
x_rotations = np.array(
[[-0.61330704, 0.41591889, -0.62297525],
[-0.74697144, 0.31388326, 0.77368233],
[-0.25668686, -0.89237972, -0.24121788]])
x_rotations_sign_flip = pls_ca.x_rotations_ / x_rotations
y_weights = np.array(
[[+0.58989127, 0.7890047, 0.1717553],
[+0.77134053, -0.61351791, 0.16920272],
[-0.23887670, -0.03267062, 0.97050016]])
y_weights_sign_flip = pls_ca.y_weights_ / y_weights
y_rotations = np.array(
[[+0.58989127, 0.7168115, 0.30665872],
[+0.77134053, -0.70791757, 0.19786539],
[-0.23887670, -0.00343595, 0.94162826]])
y_rotations_sign_flip = pls_ca.y_rotations_ / y_rotations
# x_weights = X.dot(x_rotation)
# Hence R/python sign flip should be the same in x_weight and x_rotation
assert_array_almost_equal(x_rotations_sign_flip, x_weights_sign_flip)
# This test that R / python give the same result up to column
# sign indeterminacy
assert_array_almost_equal(np.abs(x_rotations_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(x_weights_sign_flip), 1, 4)
assert_array_almost_equal(y_rotations_sign_flip, y_weights_sign_flip)
assert_array_almost_equal(np.abs(y_rotations_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(y_weights_sign_flip), 1, 4)
# 2) Regression PLS (PLS2): "Non regression test"
# ===============================================
# The results were checked against the R-packages plspm, misOmics and pls
pls_2 = pls_.PLSRegression(n_components=X.shape[1])
pls_2.fit(X, Y)
x_weights = np.array(
[[-0.61330704, -0.00443647, 0.78983213],
[-0.74697144, -0.32172099, -0.58183269],
[-0.25668686, 0.94682413, -0.19399983]])
x_weights_sign_flip = pls_2.x_weights_ / x_weights
x_loadings = np.array(
[[-0.61470416, -0.24574278, 0.78983213],
[-0.65625755, -0.14396183, -0.58183269],
[-0.51733059, 1.00609417, -0.19399983]])
x_loadings_sign_flip = pls_2.x_loadings_ / x_loadings
y_weights = np.array(
[[+0.32456184, 0.29892183, 0.20316322],
[+0.42439636, 0.61970543, 0.19320542],
[-0.13143144, -0.26348971, -0.17092916]])
y_weights_sign_flip = pls_2.y_weights_ / y_weights
y_loadings = np.array(
[[+0.32456184, 0.29892183, 0.20316322],
[+0.42439636, 0.61970543, 0.19320542],
[-0.13143144, -0.26348971, -0.17092916]])
y_loadings_sign_flip = pls_2.y_loadings_ / y_loadings
# x_loadings[:, i] = Xi.dot(x_weights[:, i]) \forall i
assert_array_almost_equal(x_loadings_sign_flip, x_weights_sign_flip, 4)
assert_array_almost_equal(np.abs(x_loadings_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(x_weights_sign_flip), 1, 4)
assert_array_almost_equal(y_loadings_sign_flip, y_weights_sign_flip, 4)
assert_array_almost_equal(np.abs(y_loadings_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(y_weights_sign_flip), 1, 4)
# 3) Another non-regression test of Canonical PLS on random dataset
# =================================================================
# The results were checked against the R-package plspm
n = 500
p_noise = 10
q_noise = 5
# 2 latents vars:
rng = check_random_state(11)
l1 = rng.normal(size=n)
l2 = rng.normal(size=n)
latents = np.array([l1, l1, l2, l2]).T
X = latents + rng.normal(size=4 * n).reshape((n, 4))
Y = latents + rng.normal(size=4 * n).reshape((n, 4))
X = np.concatenate(
(X, rng.normal(size=p_noise * n).reshape(n, p_noise)), axis=1)
Y = np.concatenate(
(Y, rng.normal(size=q_noise * n).reshape(n, q_noise)), axis=1)
pls_ca = pls_.PLSCanonical(n_components=3)
pls_ca.fit(X, Y)
x_weights = np.array(
[[0.65803719, 0.19197924, 0.21769083],
[0.7009113, 0.13303969, -0.15376699],
[0.13528197, -0.68636408, 0.13856546],
[0.16854574, -0.66788088, -0.12485304],
[-0.03232333, -0.04189855, 0.40690153],
[0.1148816, -0.09643158, 0.1613305],
[0.04792138, -0.02384992, 0.17175319],
[-0.06781, -0.01666137, -0.18556747],
[-0.00266945, -0.00160224, 0.11893098],
[-0.00849528, -0.07706095, 0.1570547],
[-0.00949471, -0.02964127, 0.34657036],
[-0.03572177, 0.0945091, 0.3414855],
[0.05584937, -0.02028961, -0.57682568],
[0.05744254, -0.01482333, -0.17431274]])
x_weights_sign_flip = pls_ca.x_weights_ / x_weights
x_loadings = np.array(
[[0.65649254, 0.1847647, 0.15270699],
[0.67554234, 0.15237508, -0.09182247],
[0.19219925, -0.67750975, 0.08673128],
[0.2133631, -0.67034809, -0.08835483],
[-0.03178912, -0.06668336, 0.43395268],
[0.15684588, -0.13350241, 0.20578984],
[0.03337736, -0.03807306, 0.09871553],
[-0.06199844, 0.01559854, -0.1881785],
[0.00406146, -0.00587025, 0.16413253],
[-0.00374239, -0.05848466, 0.19140336],
[0.00139214, -0.01033161, 0.32239136],
[-0.05292828, 0.0953533, 0.31916881],
[0.04031924, -0.01961045, -0.65174036],
[0.06172484, -0.06597366, -0.1244497]])
x_loadings_sign_flip = pls_ca.x_loadings_ / x_loadings
y_weights = np.array(
[[0.66101097, 0.18672553, 0.22826092],
[0.69347861, 0.18463471, -0.23995597],
[0.14462724, -0.66504085, 0.17082434],
[0.22247955, -0.6932605, -0.09832993],
[0.07035859, 0.00714283, 0.67810124],
[0.07765351, -0.0105204, -0.44108074],
[-0.00917056, 0.04322147, 0.10062478],
[-0.01909512, 0.06182718, 0.28830475],
[0.01756709, 0.04797666, 0.32225745]])
y_weights_sign_flip = pls_ca.y_weights_ / y_weights
y_loadings = np.array(
[[0.68568625, 0.1674376, 0.0969508],
[0.68782064, 0.20375837, -0.1164448],
[0.11712173, -0.68046903, 0.12001505],
[0.17860457, -0.6798319, -0.05089681],
[0.06265739, -0.0277703, 0.74729584],
[0.0914178, 0.00403751, -0.5135078],
[-0.02196918, -0.01377169, 0.09564505],
[-0.03288952, 0.09039729, 0.31858973],
[0.04287624, 0.05254676, 0.27836841]])
y_loadings_sign_flip = pls_ca.y_loadings_ / y_loadings
assert_array_almost_equal(x_loadings_sign_flip, x_weights_sign_flip, 4)
assert_array_almost_equal(np.abs(x_weights_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(x_loadings_sign_flip), 1, 4)
assert_array_almost_equal(y_loadings_sign_flip, y_weights_sign_flip, 4)
assert_array_almost_equal(np.abs(y_weights_sign_flip), 1, 4)
assert_array_almost_equal(np.abs(y_loadings_sign_flip), 1, 4)
# Orthogonality of weights
# ~~~~~~~~~~~~~~~~~~~~~~~~
check_ortho(pls_ca.x_weights_, "x weights are not orthogonal")
check_ortho(pls_ca.y_weights_, "y weights are not orthogonal")
# Orthogonality of latent scores
# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
check_ortho(pls_ca.x_scores_, "x scores are not orthogonal")
check_ortho(pls_ca.y_scores_, "y scores are not orthogonal")
def test_load_linnerud():
res = load_linnerud()
assert_equal(res.data.shape, (20, 3))
assert_equal(res.target.shape, (20, 3))
assert_equal(len(res.target_names), 3)
assert_true(res.DESCR)
def scikitAlgorithms_UCIDataset(input_dict):
from sklearn import datasets
allDSets = {"iris":datasets.load_iris(), "boston":datasets.load_boston(), "diabetes":datasets.load_diabetes(), " linnerud":datasets.load_linnerud()}
dataset = allDSets[input_dict['dsIn']]
output_dict = {}
output_dict['dtsOut'] = dataset#(dataset.data, dataset.target)
return output_dict
# y_test = _make_matrix_classes(y_test)
# rna.fit(X_train, y_train)
# y_pred = rna.predict(X_test)
# s = rna.score(X_test, y_test)
# print("score: {}".format(s))
with MLP(
mse_target=1e-8,
max_epochs=1e8,
hidden_layer_sizes=(6, 30, 30, 6),
output_fn=tf.nn.sigmoid,
verbose=True,
learning_rate=1e-6,
) as rna:
linnerud = load_linnerud()
ss = ShuffleSplit()
train_index, test_index = next(iter(ss.split(linnerud.data)))
X_train = linnerud.data[train_index]
y_train = linnerud.target[train_index]
X_test = linnerud.data[test_index]
y_test = linnerud.target[test_index]
X_train = np.array(X_train)
y_train = np.array(y_train)
X_test = np.array(X_test)
y_test = np.array(y_test)
norm_x = MinMaxScaler(feature_range=(0.0, 1.0), copy=True)
iris = datasets.load_breast_cancer()
print("the output of load_breast_cancer() :: ", iris)
#load_diabetes() excuted
iris = datasets.load_diabetes()
print("the output of load_diabetes() :: ", iris)
#load_digits() excuted
iris = datasets.load_digits()
print("the output of load_digits() :: ", iris)
#load_iris() excuted
print("the output of load_iris() :: ", datasets.load_iris())
#load_linnerud() excuted
print("the output of load_linnerud() :: ", datasets.load_linnerud())
#load_wine() excuted
print("the output of load_wine() :: ", datasets.load_wine())
#make_blobs() excuted
print("the output of make_blobs() :: ", datasets.make_blobs())
#make_circles() executed
print("the output of make_circles() :: ", datasets.make_circles())
#make_classification() executed
print("the output of make_classification() :: ",
datasets.make_classification())
#make_friedman1() executed
print("the output of make_friedman1() :: ", datasets.make_friedman1())
def test_update_database_dict():
sm = tm.Surrogate_Models()
variables, objectives = datasets.load_linnerud(return_X_y=True)
sm.random = 57757
test_dict = {}
i = 0
for ind, obj in zip(variables, objectives):
test_dict['core {}'.format(i)] = {
'independent variables': {},
'dependent variables': {}
}
test_dict['core {}'.format(i)]['independent variables'] = {
'a': ind[0],
'b': ind[1],
'c': ind[2]
}
test_dict['core {}'.format(i)]['dependent variables'] = {
'd': obj[0],
'e': obj[1],
'f': obj[2]
}
i += 1
sm.update_database(['a', 'b', 'c'], ['d', 'e', 'f'], database=test_dict)
ind_var_given = [[
11,
230,
80,
], [
6,
70,
31,
], [
2,
110,
43,
], [
14,
215,
105,
], [
15,
225,
73,
], [
4,
60,
25,
], [
12,
105,
37,
], [
12,
101,
101,
], [
13,
210,
115,
], [
13,
155,
58,
], [
2,
110,
60,
], [
15,
200,
40,
], [
6,
125,
40,
], [
8,
101,
38,
], [
17,
120,
38,
]]
obj_var_given = [[
157,
32,
52,
], [
193,
36,
46,
], [
138,
33,
68,
], [
154,
34,
64,
], [
156,
33,
54,
], [
176,
37,
54,
], [
162,
35,
62,
], [
193,
38,
58,
], [
166,
33,
52,
], [
189,
35,
46,
], [
189,
37,
52,
], [
176,
31,
74,
], [
167,
34,
60,
], [
211,
38,
56,
], [
169,
34,
50,
]]
np.testing.assert_array_equal(sm.var_train, ind_var_given)
np.testing.assert_array_equal(sm.obj_train, obj_var_given)
assert len(sm.var_test) == 5
assert len(sm.obj_test) == 5
test_dict = {
'core 100': {
'independent variables': {
'a': 12,
'b': 250,
'c': 85
},
'dependent variables': {
'd': 165,
'e': 33,
'f': 57
}
},
'core 101': {
'independent variables': {
'a': 12,
'b': 250,
'c': 85
},
'dependent variables': {
'd': 165,
'e': 33,
'f': 57
}
}
}
sm.update_database(['a', 'b', 'c'], ['d', 'e', 'f'], database=test_dict)
assert len(sm.var_train) == 16
assert len(sm.obj_train) == 16
assert len(sm.var_test) == 6
assert len(sm.obj_test) == 6
def test_load_linnerud():
res = load_linnerud()
assert_equal(res.data.shape, (20, 3))
assert_equal(res.target.shape, (20, 3))
assert_equal(len(res.target_names), 3)
assert_true(res.DESCR)
def main():
start_t = datetime.now()
# set built-in dataset choices
ds1 = datasets.load_boston()
ds2 = datasets.load_iris()
ds3 = datasets.load_diabetes()
ds4 = datasets.load_digits()
ds5 = datasets.load_linnerud()
ds6 = datasets.load_wine()
ds7 = datasets.load_breast_cancer()
# Get user inputs -- add error handeling
# when response is continous then no 'target_names'
# when response is catagorical set 'target_names'
print(""" Select SKLearn dataset to use: ~default is 3~
1 - boston (response is continuous)
2 - iris (response is catagorical [3 cats])
3 - diabetes (response is continuous)
4 - digits (response is an array)
5 - linnerud (response is catagorical array of continuous)[3 cats])
6 - wine (response is catagorical [3 cast])
7 - breast cancer (response is catagorical {2cats/bool])
8 - user choice
""")
choice = int(input("Which set? " or 3))
if choice == 1:
the_ds = ds1
elif choice == 2:
the_ds = ds2
elif choice == 3:
the_ds = ds3
elif choice == 4:
the_ds = ds4
elif choice == 5:
the_ds = ds5
elif choice == 6:
the_ds = ds6
elif choice == 7:
the_ds = ds7
elif choice == 8:
the_ds = input("direct path to dataset: ")
elif choice == "":
the_ds = ds3
else:
print(f"{choice} is an invalid entry. Please try again.")
print(f"You chose {choice}")
# turn source data into a pandas df
working_df = pd.DataFrame(the_ds.data, columns=the_ds.feature_names)
working_df["target"] = pd.Series(the_ds.target) # chg
working_df.head()
# get column names
col_list = working_df.columns.values.tolist()
titles = [
i.replace(")", "_").replace("(", "").replace(" ", "_")
for i in col_list
]
working_df.columns = titles
print_heading("Original Dataset")
print(working_df)
# ~RESPONSE~
# y = the_ds.target # assign the response here #chg
res_type = tot(the_ds.target)
print_heading("Response type is " + res_type)
# Group Predictor types
type_mask = [tot(working_df[i]) for i in col_list]
predictor_array = np.column_stack((col_list, type_mask))
pred_df = pd.DataFrame(predictor_array, columns=["Predictor", "Category"])
# ~PREDICTORS~
# Allow user to select the desired features
# feature_list = predictor_select(the_ds)
# enable abovce line to select only specific features to evaluate
cont_feature_df = pred_df[
pred_df["Category"] ==
"continuous"] # where tot continuous and bool_check false
try:
cont_feature_df = cont_feature_df.drop("target", axis=1, inplace=True)
except Exception:
pass
cat_feature_df = pred_df[
pred_df["Category"] !=
"continuous"] # where tot not continuous or bool_check true
try:
cat_feature_df = cat_feature_df.drop("target", axis=1, inplace=True)
except Exception:
pass
print("No Continuous!") if cont_feature_df.empty else print(
cont_feature_df)
print("No Categorical!") if cat_feature_df.empty else print(cat_feature_df)
# cont_feature_list = list(cont_feature_df["Predictor"])
# cat_feature_list = list(cat_feature_df["Predictor"])
# Make plots
# if res_type == "continuous":
cat_con_file_list = plot_cat_cont(the_ds)
con_con_file_list = plot_cont_cont(the_ds)
# else:
con_cat_file_list = plot_cont_cat(the_ds)
cat_cat_file_list = plot_cat_cat(the_ds)
# Generate Report DF
report_col = (
"Category",
"p-val_&_t-val",
"Regression",
"Logistic_Regression",
"Difference_with_mean",
"Random_Forest",
)
report_df = pd.DataFrame("", index=col_list, columns=report_col)
report_df = report_df.drop(["target"])
pred_df = pred_df.set_index(["Predictor"])
pred_df = pred_df.drop(["target"])
# Update Report with data
report_df.index.name = "Predictor"
pred_df.index = report_df.index
# add plots to report
list_to_df(pred_df, report_df, "Category")
temp_df = pd.DataFrame(cat_con_file_list, columns=["Logistic_Regression"])
list_to_df(temp_df, report_df, "Logistic_Regression")
temp_df = pd.DataFrame(con_con_file_list, columns=["Regression"])
list_to_df(temp_df, report_df, "Regression")
temp_df = pd.DataFrame(con_cat_file_list, columns=["Random_Forest"])
list_to_df(temp_df, report_df, "Random_Forest")
temp_df = pd.DataFrame(cat_cat_file_list, columns=["Difference_with_mean"])
list_to_df(temp_df, report_df, "Difference_with_mean")
# Save report to HTML
report_df.to_html("HW_report_" +
datetime.now().strftime("%Y_%m_%d-%H_%M") + ".html")
print(datetime.now() - start_t)
return