def test_linear_regression_model(datatype, algorithm, nrows, column_info):
if algorithm == "svd" and nrows > 46340:
pytest.skip("svd solver is not supported for the data that has more"
"than 46340 rows or columns if you are using CUDA version"
"10.x")
ncols, n_info = column_info
X_train, X_test, y_train, y_test = make_regression_dataset(
datatype, nrows, ncols, n_info
)
# Initialization of cuML's linear regression model
cuols = cuLinearRegression(fit_intercept=True,
normalize=False,
algorithm=algorithm)
# fit and predict cuml linear regression model
cuols.fit(X_train, y_train)
cuols_predict = cuols.predict(X_test)
if nrows < 500000:
# sklearn linear regression model initialization, fit and predict
skols = skLinearRegression(fit_intercept=True, normalize=False)
skols.fit(X_train, y_train)
skols_predict = skols.predict(X_test)
assert array_equal(skols_predict, cuols_predict, 1e-1, with_sign=True)
def test_ols(datatype, X_type, y_type, algorithm):
X = np.array([[2.0, 5.0], [6.0, 9.0], [2.0, 2.0], [2.0, 3.0]],
dtype=datatype)
y = np.dot(X, np.array([5.0, 10.0]).astype(datatype))
pred_data = np.array([[3.0, 5.0], [2.0, 5.0]]).astype(datatype)
skols = skLinearRegression(fit_intercept=True, normalize=False)
skols.fit(X, y)
cuols = cuLinearRegression(fit_intercept=True,
normalize=False,
algorithm=algorithm)
if X_type == 'dataframe':
gdf = cudf.DataFrame()
gdf['0'] = np.asarray([2, 6, 2, 2], dtype=datatype)
gdf['1'] = np.asarray([5, 9, 2, 3], dtype=datatype)
cuols.fit(gdf, y)
elif X_type == 'ndarray':
cuols.fit(X, y)
sk_predict = skols.predict(pred_data)
cu_predict = cuols.predict(pred_data).to_array()
print(sk_predict)
print(cu_predict)
# print(skols.coef_)
print(cuols.gdf_datatype)
print(y.dtype)
assert array_equal(sk_predict, cu_predict, 1e-3, with_sign=True)
def test_score_matches_sklearn_performance(self):
skLR = skLinearRegression()
skLR.fit(self.X_train, self.Y_train)
skLR_score = skLR.score(self.X_test, self.Y_test)
score = self.test_LR.score(self.X_test, self.Y_test)
np.testing.assert_almost_equal(skLR_score, score, decimal=1)
def test_weighted_linear_regression(datatype, algorithm, fit_intercept,
normalize, distribution):
nrows, ncols, n_info = 1000, 20, 10
max_weight = 10
noise = 20
X_train, X_test, y_train, y_test = make_regression_dataset(
datatype, nrows, ncols, n_info, noise=noise
)
# set weight per sample to be from 1 to max_weight
if distribution == "uniform":
wt = np.random.randint(1, high=max_weight, size=len(X_train))
elif distribution == "exponential":
wt = np.random.exponential(size=len(X_train))
else:
wt = np.random.lognormal(size=len(X_train))
# Initialization of cuML's linear regression model
cuols = cuLinearRegression(fit_intercept=fit_intercept,
normalize=normalize,
algorithm=algorithm)
# fit and predict cuml linear regression model
cuols.fit(X_train, y_train, sample_weight=wt)
cuols_predict = cuols.predict(X_test)
# sklearn linear regression model initialization, fit and predict
skols = skLinearRegression(fit_intercept=fit_intercept,
normalize=normalize)
skols.fit(X_train, y_train, sample_weight=wt)
skols_predict = skols.predict(X_test)
assert array_equal(skols_predict, cuols_predict, 1e-1, with_sign=True)
def test_linear_regression_model(datatype, algorithm, nrows, column_info):
ncols, n_info = column_info
X_train, X_test, y_train, y_test = make_regression_dataset(datatype,
nrows,
ncols,
n_info)
# Initialization of cuML's linear regression model
cuols = cuLinearRegression(fit_intercept=True,
normalize=False,
algorithm=algorithm)
# fit and predict cuml linear regression model
cuols.fit(X_train, y_train)
cuols_predict = cuols.predict(X_test)
if nrows < 500000:
# sklearn linear regression model initialization, fit and predict
skols = skLinearRegression(fit_intercept=True,
normalize=False)
skols.fit(X_train, y_train)
skols_predict = skols.predict(X_test)
assert array_equal(skols_predict, cuols_predict,
1e-1, with_sign=True)
def test_LinearRegression_fit_intercept():
np.random.seed(0)
X = np.random.random((10, 1))
y = np.random.random(10)
clf1 = LinearRegression(fit_intercept=False).fit(X, y)
clf2 = skLinearRegression(fit_intercept=False).fit(X, y)
assert_allclose(clf1.coef_, clf2.coef_)
def test_LinearRegression_fit_intercept():
np.random.seed(0)
X = np.random.random((10, 1))
y = np.random.random(10)
clf1 = LinearRegression(fit_intercept=False).fit(X, y)
clf2 = skLinearRegression(fit_intercept=False).fit(X, y)
assert_allclose(clf1.coef_, clf2.coef_)
def test_score_matches_sklearn_performance(self):
print('')
sklr = skLinearRegression()
sklr.fit(self.X_train, self.y_train)
sklr_score = sklr.score(self.X_test, self.y_test)
self.advi_lr.fit(self.X_train, self.y_train)
score = self.advi_lr.score(self.X_test, self.y_test)
npt.assert_almost_equal(sklr_score, score, decimal=1)
def test_linear_regression_model_default(datatype):
X_train, X_test, y_train, y_test = small_regression_dataset(datatype)
# Initialization of cuML's linear regression model
cuols = cuLinearRegression()
# fit and predict cuml linear regression model
cuols.fit(X_train, y_train)
cuols_predict = cuols.predict(X_test)
# sklearn linear regression model initialization and fit
skols = skLinearRegression()
skols.fit(X_train, y_train)
skols_predict = skols.predict(X_test)
assert array_equal(skols_predict, cuols_predict, 1e-1, with_sign=True)
def test_LinearRegression_err():
"""
Test that errors are correctly accounted for
By comparing to scikit-learn LinearRegression
"""
np.random.seed(0)
X = np.random.random((10, 1))
y = np.random.random(10) + 1
dy = 0.1
y = np.random.normal(y, dy)
X_fit = np.linspace(0, 1, 10)[:, None]
clf1 = LinearRegression().fit(X, y, dy)
clf2 = skLinearRegression().fit(X / dy, y / dy)
assert_allclose(clf1.coef_[1:], clf2.coef_)
assert_allclose(clf1.coef_[0], clf2.intercept_ * dy)
def test_LinearRegression_err():
"""
Test that errors are correctly accounted for
By comparing to scikit-learn LinearRegression
"""
np.random.seed(0)
X = np.random.random((10, 1))
y = np.random.random(10) + 1
dy = 0.1
y = np.random.normal(y, dy)
X_fit = np.linspace(0, 1, 10)[:, None]
clf1 = LinearRegression().fit(X, y, dy)
clf2 = skLinearRegression().fit(X / dy, y / dy)
assert_allclose(clf1.coef_[1:], clf2.coef_)
assert_allclose(clf1.coef_[0], clf2.intercept_ * dy)
def demo_helper(X, Y, learning_rate, iterations, title, x_label, y_label, x_lim=None, y_lim=None):
# Splitting the Dataset
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size= 0.33, random_state= 101)
# Custom ML linear regression module
ml_regressor = LinearRegression(learning_rate=learning_rate, iterations=iterations)
# scikit-learn linear regression module
scikit_regressor = skLinearRegression()
# Perform linear regression using both scikit-learn and ML.py library
ml_regressor.fit(X_train, y_train) # custom version
scikit_regressor.fit(X_train, y_train) # scikit-learn version
# Make predictions
mlY_pred = ml_regressor.predict(X_test)
skY_pred = scikit_regressor.predict(X_test)
# Plot the X, Y data
plt.scatter(X, Y)
plt.title(title + ": Raw Data")
plt.xlabel(x_label)
plt.ylabel(y_label)
plt.show()
# Plot the X, Y_pred data
custom_label = title + ": ML.py Linear Regression Module\nLearning Rate: " + \
str(learning_rate) + ", Iterations: " + str(iterations)
plot_regression_line(mlY_pred, X_test, y_test, x_label, y_label,
custom_label, x_range=x_lim, y_range=y_lim)
plot_regression_line(skY_pred, X_test, y_test, x_label, y_label,
title + ": scikit-learn Linear Regression Module",
x_range=x_lim, y_range=y_lim)
# Evaluate Each Model's Performance
d_ml = {
'Metrics': ['Mean Absolute Error:',
'Mean Squared Error:',
'Mean Root Squared Error:'],
'Values': [mean_absolute_error(y_test, mlY_pred),
mean_squared_error(y_test, mlY_pred),
np.sqrt(mean_squared_error(y_test, mlY_pred))]
}
d_sk = {
'Metrics': ['Mean Absolute Error:',
'Mean Squared Error:',
'Mean Root Squared Error:'],
'Values': [mean_absolute_error(y_test, skY_pred),
mean_squared_error(y_test, skY_pred),
np.sqrt(mean_squared_error(y_test, skY_pred))]
}
df_ml = pd.DataFrame(data=d_ml)
df_sk = pd.DataFrame(data=d_sk)
fig, ax = plt.subplots(2)
cell_text = []
for row in range(len(df_ml)):
cell_text.append(df_ml.iloc[row])
ax[0].set_title(title + ": ML.py Linear Regression Module\nLearning Rate: " +
str(learning_rate) + ", Iterations: " + str(iterations))
ax[0].table(cellText=cell_text, colLabels=df_ml.columns, loc='center')
ax[0].axis(False)
cell_text = []
for row in range(len(df_sk)):
cell_text.append(df_sk.iloc[row])
ax[1].set_title(title + ": scikit-learn Linear Regression Module")
ax[1].table(cellText=cell_text, colLabels=df_sk.columns, loc='center')
ax[1].axis(False)
plt.show()
print("ML.py Linear Regression Weights for y = mx + b (" + title + "):")
print("Slope:", ml_regressor.slope)
print("Intercept:", ml_regressor.intercept, "\n")
[1, 4, 5, 16, 25, 64, 125]])
result = myLinearRegression._perform_change_of_basis(
test_array1, 3, True)
if not np.array_equal(result, test_array2):
errs += "\nLinear Regression: Failed to add polynomial features"
dataset = load_dataset('basisData.pkl')
X = dataset['X']
y = dataset['y']
Xtest = dataset['Xtest']
ytest = dataset['ytest']
print(" Testing least squares no regularization")
model_mine = myLinearRegression('MSE', 1, False, None)
model_mine.fit(X, y)
model_sklearn = skLinearRegression(False)
model_sklearn.fit(X, y)
y_pred_mine = model_mine.predict(X)
y_pred_sk = model_sklearn.predict(X)
if not np.array_equal(y_pred_mine, y_pred_sk):
errs += "\nLinear Regression: did not match sklearn for Least Squares no regularization"
y_pred_mine = model_mine.predict(X, round=True)
y_pred_sk = np.round(model_sklearn.predict(X), 0)
if not np.array_equal(y_pred_mine, y_pred_sk):
errs += "\nLinear Regression: did not match sklearn for Least Squares no regularization (rounded)"
# print(" Testing least squares with L2 regularization")
# model_mine = myLinearRegression('MSE', 1, False, 'L2', 1, 1000)
# model_mine.fit(X, y)
# model_sklearn = Ridge(fit_intercept=False)
# model_sklearn.fit(X, y)
def test_linear_models(datatype, X_type, y_type, algorithm, nrows, ncols,
n_info):
train_rows = np.int32(nrows * 0.8)
X, y = make_regression(n_samples=(nrows),
n_features=ncols,
n_informative=n_info,
random_state=0)
X_test = np.asarray(X[train_rows:, 0:]).astype(datatype)
X_train = np.asarray(X[0:train_rows, :]).astype(datatype)
y_train = np.asarray(y[0:train_rows, ]).astype(datatype)
# Initialization of cuML's linear and ridge regression models
cuols = cuLinearRegression(fit_intercept=True,
normalize=False,
algorithm=algorithm)
curidge = cuRidge(fit_intercept=False, normalize=False, solver=algorithm)
if X_type == 'dataframe':
y_train = pd.DataFrame({'labels': y_train[0:, ]})
X_train = pd.DataFrame(
{'fea%d' % i: X_train[0:, i]
for i in range(X_train.shape[1])})
X_test = pd.DataFrame(
{'fea%d' % i: X_test[0:, i]
for i in range(X_test.shape[1])})
X_cudf = cudf.DataFrame.from_pandas(X_train)
X_cudf_test = cudf.DataFrame.from_pandas(X_test)
y_cudf = y_train.values
y_cudf = y_cudf[:, 0]
y_cudf = cudf.Series(y_cudf)
# fit and predict cuml linear regression model
cuols.fit(X_cudf, y_cudf)
cuols_predict = cuols.predict(X_cudf_test).to_array()
# fit and predict cuml ridge regression model
curidge.fit(X_cudf, y_cudf)
curidge_predict = curidge.predict(X_cudf_test).to_array()
elif X_type == 'ndarray':
# fit and predict cuml linear regression model
cuols.fit(X_train, y_train)
cuols_predict = cuols.predict(X_test).to_array()
# fit and predict cuml ridge regression model
curidge.fit(X_train, y_train)
curidge_predict = curidge.predict(X_test).to_array()
if nrows < 500000:
# sklearn linear and ridge regression model initialization and fit
skols = skLinearRegression(fit_intercept=True, normalize=False)
skols.fit(X_train, y_train)
skridge = skRidge(fit_intercept=False, normalize=False)
skridge.fit(X_train, y_train)
skols_predict = skols.predict(X_test)
skridge_predict = skridge.predict(X_test)
assert array_equal(skols_predict, cuols_predict, 1e-1, with_sign=True)
assert array_equal(skridge_predict,
curidge_predict,
1e-1,
with_sign=True)
def PolynomialRegression(degree=3, **kwargs):
return make_pipeline(PolynomialFeatures(degree),
skLinearRegression(**kwargs))