def test_lm(fit_intercept):
X, y = make_regression(n_samples=100, n_features=5, chunks=50)
lr = LinearRegression(fit_intercept=fit_intercept)
lr.fit(X, y)
lr.predict(X)
if fit_intercept:
assert lr.intercept_ is not None
def test_unknown_chunks_ok(fit_intercept):
# https://github.com/dask/dask-ml/issues/145
X = dd.from_pandas(pd.DataFrame(np.random.uniform(size=(10, 5))), 2).values
y = dd.from_pandas(pd.Series(np.random.uniform(size=(10, ))), 2).values
reg = LinearRegression(fit_intercept=fit_intercept)
reg.fit(X, y)
hour_no_train_label = hour_no_train.loc[:,"cnt"] hour_no_train_label.head() # Now we build the most basic model with Linear Regression # In[203]: LR = LinearRegression(fit_intercept=True) # In[204]: da.LR_model_baseline = LR.fit(hour_no_train_X.values, hour_no_train_label.values) # In[205]: da.hour_no_test_X = hour_no_test.loc[:, "season":"windspeed"] # In[206]: LR_baseline_predicted = LR_model_baseline.predict(hour_no_test_X.values) # In[207]:
["year", "hour", "is_holiday", "weekday", "is_workingday", "weathersit"]
de = DummyEncoder(
["year", "hour", "is_holiday", "weekday", "is_workingday", "weathersit"]
)
X_traintrial = de.fit_transform(X_traintrial)
de = DummyEncoder(
["year", "hour", "is_holiday", "weekday", "is_workingday", "weathersit"]
)
X_testtrial = de.fit_transform(X_testtrial)
)
lr = LinearRegression()
lr.fit(X_traintrial.values, y_traintrial.values)
X_testtrial = X_testtrial.drop("season", axis=1)
y_predtrial = lr.predict(X_traintrial.values)
y_predtest = lr.predict(X_testtrial.values)
import dask.array as da
y_predtest.compute()
# random forest
rf = RandomForestRegressor(n_estimators=1000, max_depth=10)
def test_lr_score():
X = da.from_array(np.arange(1000).reshape(1000, 1))
lr = LinearRegression()
lr.fit(X, X)
assert lr.score(X, X) == pytest.approx(1, 0.001)
categorical_variables = df[[
'Gender', 'Age', 'Occupation', 'City_Category',
'Stay_In_Current_City_Years', 'Marital_Status'
]]
target = df['Purchase']
#creating dummies for the categorical variables
data = dd.get_dummies(categorical_variables.categorize()).compute()
#converting dataframe to array
datanew = data.values
#fit the model
from dask_ml.linear_model import LinearRegression
lr = LinearRegression()
lr.fit(datanew, target)
#preparing the test data
test_categorical = test[[
'Gender', 'Age', 'Occupation', 'City_Category',
'Stay_In_Current_City_Years', 'Marital_Status'
]]
test_dummy = dd.get_dummies(test_categorical.categorize()).compute()
testnew = test_dummy.values
#predict on test and upload
pred = lr.predict(testnew)
#Clustering/K-Means
from dask_ml.cluster import KMeans
model = KMeans()
def image_tikhonov(self,
vis_arr,
sphere,
alpha,
scale=True,
usedask=False):
n_s = sphere.pixels.shape[0]
n_v = self.u_arr.shape[0]
lambduh = alpha / np.sqrt(n_s)
if not usedask:
gamma = self.make_gamma(sphere)
logger.info("augmented: {}".format(gamma.shape))
vis_aux = vis_to_real(vis_arr)
logger.info("vis mean: {} shape: {}".format(
np.mean(vis_aux), vis_aux.shape))
tol = min(alpha / 1e4, 1e-10)
logger.info("Solving tol={} ...".format(tol))
# reg = linear_model.ElasticNet(alpha=alpha/np.sqrt(n_s),
# tol=1e-6,
# l1_ratio = 0.01,
# max_iter=100000,
# positive=True)
if False:
(
sky,
lstop,
itn,
r1norm,
r2norm,
anorm,
acond,
arnorm,
xnorm,
var,
) = scipy.sparse.linalg.lsqr(gamma,
vis_aux,
damp=alpha,
show=True)
logger.info(
"Alpha: {}: Iterations: {}: rnorm: {}: xnorm: {}".format(
alpha, itn, r2norm, xnorm))
else:
reg = linear_model.Ridge(alpha=alpha,
tol=tol,
solver="lsqr",
max_iter=100000)
reg.fit(gamma, vis_aux)
logger.info(" Solve Complete, iter={}".format(reg.n_iter_))
sky = da.from_array(reg.coef_)
residual = vis_aux - gamma @ sky
sky, residual_norm, solution_norm = da.compute(
sky,
np.linalg.norm(residual)**2,
np.linalg.norm(sky)**2)
score = reg.score(gamma, vis_aux)
logger.info("Alpha: {}: Loss: {}: rnorm: {}: snorm: {}".format(
alpha, score, residual_norm, solution_norm))
else:
from dask_ml.linear_model import LinearRegression
import dask_glm
from dask.distributed import Client, LocalCluster
from dask.diagnostics import ProgressBar
import dask
logger.info("Starting Dask Client")
if True:
cluster = LocalCluster(dashboard_address=":8231",
processes=False)
client = Client(cluster)
else:
client = Client("tcp://localhost:8786")
logger.info("Client = {}".format(client))
harmonic_list = []
p2j = 2 * np.pi * 1.0j
dl = sphere.l
dm = sphere.m
dn = sphere.n
n_arr_minus_1 = dn - 1
du = self.u_arr
dv = self.v_arr
dw = self.w_arr
for u, v, w in zip(du, dv, dw):
harmonic = da.from_array(
np.exp(p2j * (u * dl + v * dm + w * n_arr_minus_1)) /
np.sqrt(sphere.npix),
chunks=(n_s, ),
)
harminc = client.persist(harmonic)
harmonic_list.append(harmonic)
gamma = da.stack(harmonic_list)
logger.info("Gamma Shape: {}".format(gamma.shape))
# gamma = gamma.reshape((n_v, n_s))
gamma = gamma.conj()
gamma = client.persist(gamma)
logger.info("Gamma Shape: {}".format(gamma.shape))
logger.info("Building Augmented Operator...")
proj_operator_real = da.real(gamma)
proj_operator_imag = da.imag(gamma)
proj_operator = da.block([[proj_operator_real],
[proj_operator_imag]])
proj_operator = client.persist(proj_operator)
logger.info("Proj Operator shape {}".format(proj_operator.shape))
vis_aux = da.from_array(
np.array(
np.concatenate((np.real(vis_arr), np.imag(vis_arr))),
dtype=np.float32,
))
# logger.info("Solving...")
en = dask_glm.regularizers.ElasticNet(weight=0.01)
en = dask_glm.regularizers.L2()
# dT = da.from_array(proj_operator, chunks=(-1, 'auto'))
##dT = da.from_array(proj_operator, chunks=(-1, 'auto'))
# dv = da.from_array(vis_aux)
dask.config.set({"array.chunk-size": "1024MiB"})
A = da.rechunk(proj_operator, chunks=("auto", n_s))
A = client.persist(A)
y = vis_aux # da.rechunk(vis_aux, chunks=('auto', n_s))
y = client.persist(y)
# sky = dask_glm.algorithms.proximal_grad(A, y, regularizer=en, lambduh=alpha, max_iter=10000)
logger.info("Rechunking completed.. A= {}.".format(A.shape))
reg = LinearRegression(
penalty=en,
C=1.0 / lambduh,
fit_intercept=False,
solver="lbfgs",
max_iter=1000,
tol=1e-8,
)
sky = reg.fit(A, y)
sky = reg.coef_
score = reg.score(proj_operator, vis_aux)
logger.info("Loss function: {}".format(score.compute()))
logger.info("Solving Complete: sky = {}".format(sky.shape))
sphere.set_visible_pixels(sky, scale=False)
return sky.reshape(-1, 1)
from dask.distributed import Client
import time
import sys
from dask_ml.linear_model import LinearRegression
import dask.dataframe as dd
client = Client(n_workers=4)
t0 = time.time()
data = dd.read_csv(sys.argv[1], header=None)
model = LinearRegression(fit_intercept=False)
reg = model.fit(
data[[
0, 1, 2, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 20, 21
]].values, data[3].values)
print(reg.coef_)
print('Tiempo transcurrido:', time.time() - t0)
client.close()
def image_tikhonov(self, vis_arr, sphere, alpha, scale=True, usedask=False):
n_s = sphere.pixels.shape[0]
n_v = self.u_arr.shape[0]
lambduh = alpha/np.sqrt(n_s)
if not usedask:
gamma = self.make_gamma(sphere)
logger.info("Building Augmented Operator...")
proj_operator_real = np.real(gamma).astype(np.float32)
proj_operator_imag = np.imag(gamma).astype(np.float32)
gamma = None
proj_operator = np.block([[proj_operator_real], [proj_operator_imag]])
proj_operator_real = None
proj_operator_imag = None
logger.info('augmented: {}'.format(proj_operator.shape))
vis_aux = np.array(np.concatenate((np.real(vis_arr), np.imag(vis_arr))), dtype=np.float32)
logger.info('vis mean: {} shape: {}'.format(np.mean(vis_aux), vis_aux.shape))
logger.info("Solving...")
reg = linear_model.ElasticNet(alpha=lambduh, l1_ratio=0.05, max_iter=10000, positive=True)
reg.fit(proj_operator, vis_aux)
sky = reg.coef_
score = reg.score(proj_operator, vis_aux)
logger.info('Loss function: {}'.format(score))
else:
from dask_ml.linear_model import LinearRegression
import dask_glm
import dask.array as da
from dask.distributed import Client, LocalCluster
from dask.diagnostics import ProgressBar
import dask
logger.info('Starting Dask Client')
if True:
cluster = LocalCluster(dashboard_address=':8231', processes=False)
client = Client(cluster)
else:
client = Client('tcp://localhost:8786')
logger.info("Client = {}".format(client))
harmonic_list = []
p2j = 2*np.pi*1.0j
dl = sphere.l
dm = sphere.m
dn = sphere.n
n_arr_minus_1 = dn - 1
du = self.u_arr
dv = self.v_arr
dw = self.w_arr
for u, v, w in zip(du, dv, dw):
harmonic = da.from_array(np.exp(p2j*(u*dl + v*dm + w*n_arr_minus_1)) / np.sqrt(sphere.npix), chunks=(n_s,))
harminc = client.persist(harmonic)
harmonic_list.append(harmonic)
gamma = da.stack(harmonic_list)
logger.info('Gamma Shape: {}'.format(gamma.shape))
#gamma = gamma.reshape((n_v, n_s))
gamma = gamma.conj()
gamma = client.persist(gamma)
logger.info('Gamma Shape: {}'.format(gamma.shape))
logger.info("Building Augmented Operator...")
proj_operator_real = da.real(gamma)
proj_operator_imag = da.imag(gamma)
proj_operator = da.block([[proj_operator_real], [proj_operator_imag]])
proj_operator = client.persist(proj_operator)
logger.info("Proj Operator shape {}".format(proj_operator.shape))
vis_aux = da.from_array(np.array(np.concatenate((np.real(vis_arr), np.imag(vis_arr))), dtype=np.float32))
#logger.info("Solving...")
en = dask_glm.regularizers.ElasticNet(weight=0.01)
en = dask_glm.regularizers.L2()
#dT = da.from_array(proj_operator, chunks=(-1, 'auto'))
##dT = da.from_array(proj_operator, chunks=(-1, 'auto'))
#dv = da.from_array(vis_aux)
dask.config.set({'array.chunk-size': '1024MiB'})
A = da.rechunk(proj_operator, chunks=('auto', n_s))
A = client.persist(A)
y = vis_aux # da.rechunk(vis_aux, chunks=('auto', n_s))
y = client.persist(y)
#sky = dask_glm.algorithms.proximal_grad(A, y, regularizer=en, lambduh=alpha, max_iter=10000)
logger.info("Rechunking completed.. A= {}.".format(A.shape))
reg = LinearRegression(penalty=en, C=1.0/lambduh,
fit_intercept=False,
solver='lbfgs',
max_iter=1000, tol=1e-8 )
sky = reg.fit(A, y)
sky = reg.coef_
score = reg.score(proj_operator, vis_aux)
logger.info('Loss function: {}'.format(score.compute()))
logger.info("Solving Complete: sky = {}".format(sky.shape))
sphere.set_visible_pixels(sky, scale=True)
return sky.reshape(-1,1)
client = Client()
client
# #### Linear Regression
# In[44]:
from scikitplot.metrics import plot_calibration_curve
from scikitplot.plotters import plot_learning_curve
from scikitplot.estimators import plot_feature_importances
# In[45]:
lr = LinearRegression()
with joblib.parallel_backend('dask'):
lr_model = lr.fit(X_train.values, y_train.values)
y_pred_lr = lr.predict(X_test.values)
# In[46]:
mse(y_test.values, y_pred_lr)
# In[47]:
r2_score(y_test.values.compute(), y_pred_lr.compute())
# ### Non Linear Models
# #### Random Forest Regressor
# In[48]: