def elasticNet(X,y):
print("\n### ~~~~~~~~~~~~~~~~~~~~ ###")
print("Lasso Regression")
### ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
myDegree = 40
polynomialFeatures = PolynomialFeatures(degree=myDegree, include_bias=False)
Xp = polynomialFeatures.fit_transform(X)
myScaler = StandardScaler()
scaled_Xp = myScaler.fit_transform(Xp)
### ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
elasticNet = ElasticNet(alpha=1e-7,l1_ratio=0.5)
elasticNet.fit(scaled_Xp,y)
### ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
dummyX = np.arange(0,2,0.01)
dummyX = dummyX.reshape((dummyX.shape[0],1))
dummyXp = polynomialFeatures.fit_transform(dummyX)
scaled_dummyXp = myScaler.transform(dummyXp)
dummyY = elasticNet.predict(scaled_dummyXp)
outputFILE = 'plot-elasticNet.png'
fig, ax = plt.subplots()
fig.set_size_inches(h = 6.0, w = 10.0)
ax.axis([0,2,0,15])
ax.scatter(X,y,color="black",s=10.0)
ax.plot(dummyX, dummyY, color='red', linewidth=1.5)
plt.savefig(filename = outputFILE, bbox_inches='tight', pad_inches=0.2, dpi = 600)
### ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
return( None )
def check_ElasticNet(X, y, pred, tol, reg_alpha, reg_lambda, weights):
enet = ElasticNet(alpha=reg_alpha + reg_lambda,
l1_ratio=reg_alpha / (reg_alpha + reg_lambda))
enet.fit(X, y)
enet_pred = enet.predict(X)
assert np.isclose(weights, enet.coef_, rtol=tol, atol=tol).all()
assert np.isclose(enet_pred, pred, rtol=tol, atol=tol).all()
def report_ff_en():
# Fastfood approximation of Gaussian kernel
para = FastfoodPara(n, d)
st = time()
PHI_train, _ = FastfoodForKernel(trainData, para, sgm)
elapsed_ff_kern_train = time() - st
st = time()
PHI_valid, _ = FastfoodForKernel(validationData, para, sgm)
elapsed_ff_kern_valid = time() - st
# Train elastic net on projected training data
en = ElasticNet()
st = time()
en.fit(PHI_train.T, trainLabels)
elapsed_en_fit = time() - st
# Predict labels for projected validation data
st = time()
y_pred = en.predict(PHI_valid.T)
elapsed_en_pred = time() - st
# Report performance
mse_proj = metrics.mean_squared_error(validationLabels, y_pred)
# print("For projected data, MSE = {:0.4g}.".format(mse_proj))
return mse_proj, elapsed_en_fit, elapsed_ff_kern_train
def enet(a):
print ("Doing elastic net")
clf3 = ElasticNet(alpha=a)
clf3.fit(base_X, base_Y)
print ("Score = %f" % clf3.score(base_X, base_Y))
clf3_pred = clf3.predict(X_test)
write_to_file("elastic.csv", clf3_pred)
def enet_granger_causality_test(X_t, y_t, top_df, max_iter=10000000):
"""
Return the cv-parameters tested across the whole data
:param X_t:
:param y_t:
:param top_df:
:return: res_df, test_betas
"""
test_errs = np.zeros(len(top_df))
scores = np.zeros(len(top_df))
dfs = np.zeros(len(top_df))
test_coefs = np.zeros((len(top_df), X_t.shape[1]))
for i in range(len(top_df)):
alpha = top_df.iloc[i]["alpha"]
lambda_min = top_df.iloc[i]["lambda.min"]
enet = ElasticNet(l1_ratio=alpha, alpha=lambda_min, max_iter=max_iter)
enet.fit(X_t, y_t)
y_pred = enet.predict(X_t)
test_errs[i] = np.average((y_t - y_pred)**2)
scores[i] = enet.score(X_t, y_t)
test_coefs[i] = enet.coef_
dfs[i] = len(np.where(enet.coef_)[0])
top_df["test_err"] = test_errs
top_df["score"] = scores
top_df["df"] = dfs
return top_df, test_coefs
def fit_enet(train_X, train_y, test_X):
"""
Use linear regression to predict. Elastic net is LR with L1 and L2
regularisation.
:param train_X:
:param train_y:
:param test_X:
:return:
"""
enet = ElasticNet()
enet.fit(train_X, train_y)
model = "ElasticNet int %.2f coefs %s" % (enet.intercept_, pprint(enet.coef_))
yhat_train = enet.predict(train_X)
yhat_test = enet.predict(test_X)
return model, yhat_train, yhat_test
def ElasticNetRegression(input_dict): # from sklearn.datasets import load_iris # from sklearn import tree # iris = load_iris() # clf = tree.DecisionTreeClassifier() # clf = clf.fit(iris.data, iris.target) from sklearn.datasets import load_diabetes dta = load_diabetes() n_sample = dta.data n_feature = dta.target print "*******SAMPLES********" print n_sample print "******FEARTURES*******" print n_feature from sklearn.linear_model import ElasticNet rgs = ElasticNet().fit(n_sample, n_feature) print rgs print rgs.predict(n_sample)
def fit_model_12(self,toWrite=False):
model = ElasticNet(alpha=1.0)
for data in self.cv_data:
X_train, X_test, Y_train, Y_test = data
model.fit(X_train,Y_train)
pred = model.predict(X_test)
print("Model 12 score %f" % (logloss(Y_test,pred),))
if toWrite:
f2 = open('model12/model.pkl','w')
pickle.dump(model,f2)
f2.close()
def predict_linear(self, enet=True):
"""How well can we do on this SRFF with a linear regression
(with optional elastic-net regularisation)?"""
if enet:
clf = ElasticNet()
else:
clf = LinearRegression()
# we have to transpose X here because sklearn uses the
# opposite order (rows v columns). maybe this is a sign that
# I'm using the wrong order.
clf.fit(self.train_X.T, self.train_y)
yhat = clf.predict(self.test_X.T)
err = self.defn(self.test_y, yhat)
return clf.intercept_, clf.coef_, err
def report_orig_en():
# Train elastic net on original training data
en = ElasticNet()
st = time()
en.fit(trainData.T, trainLabels)
elapsed_en_fit = time() - st
# Predict labels for original validation data
st = time()
y_pred = en.predict(validationData.T)
elapsed_en_pred = time() - st
# Report performance
mse_orig = metrics.mean_squared_error(validationLabels, y_pred)
return mse_orig, elapsed_en_fit, 0.
def create_ml_classifier(df):
import operator
X = np.array(df.drop('base_ip_release',1))
y = np.array(df['base_ip_release'])
#clf = LinearRegression()
clf = ElasticNet(alpha=1,l1_ratio=0.5)
#clf = Ridge(alpha=2)
# train_X,test_X,train_y,test_y = cross_validation.train_test_split(X,y,train_size=0.9)
#
#
# sc = StandardScaler()
# sc.fit(train_X)
# X_train_std = sc.transform(train_X)
# X_test_std = sc.transform(test_X)
#
# clf.fit(X_train_std,train_y)
# print clf.predict(X_test_std)
# print accuracy_score(test_y,clf.predict(X_test_std))
c = np.zeros(len(X)/10)
kf = k(len(y),n_folds=10)
c = 0
min_dict = {}
get_error = []
for train,test in kf:
get_clif = clf.fit(X[train],y[train])
p = clf.predict(X[test])
#print p
e = (p - y[test])
#print e, len(e)
t = np.dot(e,e)
# print t
c += t
# print c
#print p, y[test]
min_dict[t] = get_clif
get_error.append(t)
#print min_dict
min_error = min(get_error)
print sorted(min_dict.items(),key=operator.itemgetter(0))
print min_dict[min_error]
print c
print np.sqrt(c/len(X))
return min_dict[min_error]
def assert_regression_result(results, tol):
regression_results = [r for r in results if
r["param"]["objective"] == "reg:linear"]
for res in regression_results:
X = scale(res["dataset"].X,
with_mean=isinstance(res["dataset"].X, np.ndarray))
y = res["dataset"].y
reg_alpha = res["param"]["alpha"]
reg_lambda = res["param"]["lambda"]
pred = res["bst"].predict(xgb.DMatrix(X))
weights = xgb_get_weights(res["bst"])[1:]
enet = ElasticNet(alpha=reg_alpha + reg_lambda,
l1_ratio=reg_alpha / (reg_alpha + reg_lambda))
enet.fit(X, y)
enet_pred = enet.predict(X)
assert np.isclose(weights, enet.coef_, rtol=tol,
atol=tol).all(), (weights, enet.coef_)
assert np.isclose(enet_pred, pred, rtol=tol, atol=tol).all(), (
res["dataset"].name, enet_pred[:5], pred[:5])
def Lasso():
from sklearn.linear_model import Lasso
from sklearn.metrics import r2_score
alpha = 0.1
lasso = Lasso(alpha=alpha)
trainDat = shortData
trainLab = shortLabels
lassoPred = lasso.fit(trainDat,trainLab)
labPredict = lassoPred.predict(testDat)
r2val = r2_score(testLab,labPredict)
print(lasso)
print "r^2 for lasso testing is: ", r2val
from sklearn.linear_model import ElasticNet
enet = ElasticNet(alpha=alpha, l1_ratio = 0.7)
enetPred = enet.fit(trainDat, trainLab)
labPredict_enet = enet.predict(testDat)
r2val_enet = r2_score(testLab, labPredict_enet)
print enet
print "r^2 for enet testing is: ", r2val_enet
# Baysian Ridge Regression print 'baysian ridge' br = BayesianRidge(compute_score=True) #br.fit(x[:, np.newaxis], y) #br_sts_scores = br.predict(xt[:, np.newaxis]) br.fit(x, y) br_sts_scores = br.predict(xt) # Elastic Net print 'elastic net' enr = ElasticNet() #enr.fit(x[:, np.newaxis], y) #enr_sts_scores = enr.predict(xt[:, np.newaxis]) enr.fit(x, y) enr_sts_scores = enr.predict(xt) # Passive Aggressive Regression print 'passive aggressive' par = PassiveAggressiveRegressor() par.fit(x, y) par_sts_scores = par.predict(xt) #par.fit(x[:, np.newaxis], y) #par_sts_scores = par.predict(xt[:, np.newaxis]) # RANSAC Regression print 'ransac' ransac = RANSACRegressor() #ransac.fit(x[:, np.newaxis], y) #ransac_sts_scores = ransac.predict(xt[:, np.newaxis])
WBC = 7.13914
Urine = 3739.39
PatientX = np.array([[ICD9_code, Oxygen, PO2, Bicarbonate, Bilirubin, Sodium, Urea_Nitrogen,
Potassium, WBC, Urine, Age, Gender, Admission_Type, Admissin_Location,
Insurance, Religion, Marital_Status, Ethnicity, Diagnosis]])
# In[55]:
#Prediction using the Elastic NET Model
model_Elnet = ElasticNet(alpha = 0.01, l1_ratio = 0.1)
model_Elnet.fit(x_train_res, y_train_res)
y_patientX = model_Elnet.predict(PatientX)
if y_patientX > 0.5:
y_pred_px = "POSITIVE"
prob = 100*y_patientX
else:
y_pred_px = "NEGATIVE"
prob = 100 - 100*y_patientX
print("The newly addmited patient has been classified %s for the death prediction.With a probability of %f %%" % (y_pred_px,prob))
# In[73]:
from sklearn.preprocessing import normalize
def Final_Stacking(Train_DS, y, Actual_DS, Sample_DS):
print("***************Starting Final Stacking*************** at Time: %s" %(tm.strftime("%H:%M:%S")))
t0 = time()
#Setting Standard scaler for data
# stdScaler = StandardScaler()
# stdScaler.fit(Train_DS,y)
# Train_DS = stdScaler.transform(Train_DS)
# Actual_DS = stdScaler.transform(Actual_DS)
#CV: 0.36225ff
# clf = RandomForestRegressor(n_estimators=100,min_samples_leaf=18,max_features=None,bootstrap=True,
# min_samples_split=23,max_depth=25)
# clf=Lasso(alpha=0.02)
# print("lasso CV")
# Nfold_score = Nfold_Cross_Valid(Train_DS, y, clf)
#clf = xgb.XGBRegressor(n_estimators=2000,max_depth=1,learning_rate=0.01,nthread=4,min_child_weight=7,subsample=1,colsample_bytree=0.7,silent=True,gamma=0.8)
#cv:0.3872
#clf = ExtraTreesRegressor(n_estimators=1000,min_samples_leaf=19,max_features=12,bootstrap=True,min_samples_split=1,max_depth=25,n_jobs=-1)
#################################################################################################################################################
#CV:
# clf = RandomForestRegressor(n_estimators=1000,n_jobs=-1)
# #Nfold_score = Nfold_Cross_Valid(Train_DS, y, clf)
# clf.fit(Train_DS, y)
# Pred_Actual = clf.predict(Actual_DS).reshape(-1,1)
# preds_RFR = pd.DataFrame(Pred_Actual,columns=Sample_DS.columns[1:]).reset_index().sort(columns='Hazard',ascending= True).reset_index(drop=True).reset_index().sort(columns='index',ascending= True).reset_index(drop=True)
# preds_RFR = preds_RFR.drop(['Hazard','index'], axis = 1)
#
# preds = pd.DataFrame(np.array(preds_RFR), index=Sample_DS.Id.values, columns=Sample_DS.columns[1:])
# preds.to_csv(file_path+'output/Submission_Stacking_RFR_1.csv', index_label='Id')
# print("RFR Actual Model predicted")
# print(preds_RFR.head(10))
#
# sys.exit(0)
################################################################################################################################################
#CV:0.39009654989438813
# clf = xgb.XGBRegressor(n_estimators=2000,max_depth=2,learning_rate=0.01,nthread=4,min_child_weight=23,subsample=0.9,colsample_bytree=0.2,silent=True,gamma=0.9)
# #clf = xgb.XGBRegressor(n_estimators=1000)
# #Nfold_score = Nfold_Cross_Valid(Train_DS, y, clf)
# clf.fit(Train_DS, y)
# Pred_Actual = clf.predict(Actual_DS).reshape(-1,1)
# preds_XGB = pd.DataFrame(Pred_Actual,columns=Sample_DS.columns[1:]).reset_index().sort(columns='Hazard',ascending= True).reset_index(drop=True).reset_index().sort(columns='index',ascending= True).reset_index(drop=True)
# preds_XGB = preds_XGB.drop(['Hazard','index'], axis = 1)
#
# preds = pd.DataFrame(np.array(preds_XGB), index=Sample_DS.Id.values, columns=Sample_DS.columns[1:])
# preds.to_csv(file_path+'output/Submission_Stacking_XGB_1.csv', index_label='Id')
# print("XGB Actual Model predicted")
# print(preds_XGB.head(10))
#################################################################################################################################################
#CV: 0.3879 , LB:0.382419
#clf = ElasticNet(alpha=0.1, l1_ratio=0.3)
#CV:0.3902-.3905 , 0.385
clf = ElasticNet(alpha=0.1, l1_ratio=0.1)
clf = BayesianRidge(n_iter=300)
Nfold_score = Nfold_Cross_Valid(Train_DS, y, clf)
clf.fit(Train_DS, y)
Pred_Actual = clf.predict(Actual_DS).reshape(-1,1)
preds_ELN = pd.DataFrame(Pred_Actual,columns=Sample_DS.columns[1:]).reset_index().sort(columns='Hazard',ascending= True).reset_index(drop=True).reset_index().sort(columns='index',ascending= True).reset_index(drop=True)
preds_ELN = preds_ELN.drop(['Hazard','index'], axis = 1)
preds = pd.DataFrame(np.array(preds_ELN), index=Sample_DS.Id.values, columns=Sample_DS.columns[1:])
preds.to_csv(file_path+'output/Submission_Stacking_ELN_1.csv', index_label='Id')
print("ELN Actual Model predicted")
print(preds_ELN.head(10))
sys.exit(0)
#######################################################################################################################################
Pred_Actual = NN1_Regressor(Train_DS, y, Actual_DS, grid= False)
preds_NNT = pd.DataFrame(Pred_Actual,columns=Sample_DS.columns[1:]).reset_index().sort(columns='Hazard',ascending= True).reset_index(drop=True).reset_index().sort(columns='index',ascending= True).reset_index(drop=True)
preds_NNT = preds_NNT.drop(['Hazard','index'], axis = 1)
preds = pd.DataFrame(np.array(preds_NNT), index=Sample_DS.Id.values, columns=Sample_DS.columns[1:])
preds.to_csv(file_path+'output/Submission_Stacking_NNT_1.csv', index_label='Id')
print("NNT Actual Model predicted")
print(preds_NNT.head(10))
pred_Actual = (preds_XGB['level_0'] + preds_ELN['level_0'] + preds_NNT['level_0'])/3
#pred_Actual = np.power((Pred_Actual * Pred_Actual1 * Pred_Actual2), (1/3.0))
#Get the predictions for actual data set
preds = pd.DataFrame(pred_Actual, index=Sample_DS.Id.values, columns=Sample_DS.columns[1:])
preds.to_csv(file_path+'output/Submission_Stacking_1.csv', index_label='Id')
########################################################################################################################################
print("***************Ending Final Stacking*************** at Time: %s" %(tm.strftime("%H:%M:%S")))
return pred_Actual
def get_en_prediction(train_data, train_truth, test_data, test_truth, alpha=1.0, l1_ratio=0.5, iter_id=0):
clf = ElasticNet(alpha=alpha, l1_ratio=l1_ratio)
clf.fit(train_data, train_truth)
predicted = clf.predict(test_data)
return predicted.ravel()
#%%
#now for the estimation
#split into test & train set
train_X,test_X,train_Y,test_Y = train_test_split(lagged_stimuli,Y,test_size=0.3)
#%%
#try elastic net CV
#enet_model = ElasticNetCV([.1,.3,.7,.9,.99],cv=3,n_jobs=-1)
#enet_model.train(train_X,train_Y)
#pred_Y = enet_model.predict(train_X)
#for now
enet = ElasticNet(l1_ratio=0.7)
enet.fit(train_X,train_Y)
pred_Y = enet.predict(train_X)
#%%
#non-linearity first by CV NN
parameters_NN = { 'n_neighbors' : [5,10,20,40]}
NN_nonl = KNeighborsRegressor()
gs_NN = grid_search.RandomizedSearchCV(NN_nonl,parameters_NN,verbose=1)
#%%
#try Radius Neighbors Regr
#parameters_radius = { 'weights' : ('uniform','distance') , 'radius' : [0.5,1.0,3.0,5.0,10.0,20.0]}
#RN_nonl = RadiusNeighborsRegressor()
#gs_RN = grid_search.RandomizedSearchCV(RN_nonl,parameters_radius,verbose=1)
#%%
# It is made available under the MIT License
import numpy as np
from sklearn.datasets import load_svmlight_file
from sklearn.cross_validation import KFold
from sklearn.linear_model import ElasticNet
from sklearn.metrics import mean_squared_error, r2_score
data, target = load_svmlight_file('data/E2006.train')
# Edit the lines below if you want to switch method:
# met = LinearRegression(fit_intercept=True)
met = ElasticNet(fit_intercept=True, alpha=.1)
kf = KFold(len(target), n_folds=5)
pred = np.zeros_like(target)
for train, test in kf:
met.fit(data[train], target[train])
pred[test] = met.predict(data[test])
print('[EN 0.1] RMSE on testing (5 fold), {:.2}'.format(np.sqrt(mean_squared_error(target, pred))))
print('[EN 0.1] R2 on testing (5 fold), {:.2}'.format(r2_score(target, pred)))
print('')
met.fit(data, target)
pred = met.predict(data)
print('[EN 0.1] RMSE on training, {:.2}'.format(np.sqrt(mean_squared_error(target, pred))))
print('[EN 0.1] R2 on training, {:.2}'.format(r2_score(target, pred)))
mean = X_train.mean(axis=0)
X_train = (X_train - mean) / std
X_test = (X_test - mean) / std
std = y_train.std(axis=0)
mean = y_train.mean(axis=0)
y_train = (y_train - mean) / std
y_test = (y_test - mean) / std
gc.collect()
print("- benchmarking ElasticNet")
clf = ElasticNet(alpha=alpha, l1_ratio=0.5, fit_intercept=False)
tstart = time()
clf.fit(X_train, y_train)
elnet_results[i, j,
0] = mean_squared_error(clf.predict(X_test), y_test)
elnet_results[i, j, 1] = time() - tstart
gc.collect()
print("- benchmarking SGD")
clf = SGDRegressor(alpha=alpha / n_train,
fit_intercept=False,
max_iter=max_iter,
learning_rate="invscaling",
eta0=.01,
power_t=0.25,
tol=1e-3)
tstart = time()
clf.fit(X_train, y_train)
sgd_results[i, j, 0] = mean_squared_error(clf.predict(X_test),
class ElasticNet(Model):
# X represents the features, Y represents the labels
X = None
Y = None
prediction = None
model = None
def __init__(self):
pass
def __init__(self, X=None, Y=None, label_headers=None, l1_ratio=1, type='regressor', cfg=False):
if X is not None:
self.X = X
if Y is not None:
self.Y = Y
self.type = type
self.cfg = cfg
self.mapping_dict = None
self.label_headers = label_headers
self.model = ElasticNetModel(l1_ratio=l1_ratio)
def fit(self, X=None, Y=None):
if X is not None:
self.X = X
if Y is not None:
self.Y = Y
if self.type == 'classifier':
self.Y = self.map_str_to_number(self.Y)
print('ElasticNet Train started............')
self.model.fit(self.X, self.Y)
print('ElasticNet completed..........')
return self.model
def predict(self, test_features):
print('Prediction started............')
self.predictions = self.model.predict(test_features)
if self.type == 'classifier':
predictions = predictions.round()
print('Prediction completed..........')
return self.predictions
def save(self):
if self.cfg:
f = open('elasticnet_configs.txt', 'w')
f.write(json.dumps(self.model.get_params()))
f.close()
print('No models will be saved for elasticnet')
def featureImportance(self):
return self.model.coef_
def map_str_to_number(self, Y):
mapping_flag = False
if self.mapping_dict is not None:
for label_header in self.label_headers:
Y[label_header] = Y[label_header].map(self.mapping_dict)
return Y
mapping_dict = None
for label_header in self.label_headers:
check_list = pd.Series(Y[label_header])
for item in check_list:
if type(item) == str:
mapping_flag = True
break
if mapping_flag:
classes = Y[label_header].unique()
mapping_dict = {}
index = 0
for c in classes:
mapping_dict[c] = index
index += 1
Y[label_header] = Y[label_header].map(mapping_dict)
mapping_flag = False
self.mapping_dict = mapping_dict
return Y
def map_number_to_str(self, Y, classes):
Y = Y.round()
Y = Y.astype(int)
if self.mapping_dict is not None:
mapping_dict = self.mapping_dict
else:
mapping_dict = {}
index = 0
for c in classes:
mapping_dict[index] = c
index += 1
inv_map = {v: k for k, v in mapping_dict.items()}
return Y.map(inv_map)
def getAccuracy(self, test_labels, predictions, origin=0, hitmissr=0.8):
if self.type == 'classifier':
correct = 0
df = pd.DataFrame(data=predictions.flatten())
test_labels = self.map_str_to_number(test_labels.copy())
for i in range(len(df)):
if (df.values[i] == test_labels.values[i]):
correct = correct + 1
else:
correct = 0
df = pd.DataFrame(data=predictions.flatten())
for i in range(len(df)):
if 1 - abs(df.values[i] - test_labels.values[i])/abs(df.values[i]) >= hitmissr:
correct = correct + 1
return float(correct)/len(df)
def getConfusionMatrix(self, test_labels, predictions, label_headers):
df = pd.DataFrame(data=predictions.flatten())
if self.type == 'classifier':
index = 0
for label_header in label_headers:
classes = test_labels[label_header].unique()
df_tmp = self.map_number_to_str(df.ix[:,index], classes)
title = 'Normalized confusion matrix for NeuralNetwork (' + label_header + ')'
self.plot_confusion_matrix(test_labels.ix[:,index], df_tmp, classes=classes, normalize=True,
title=title)
index = index + 1
else:
return 'No Confusion Matrix for Regression'
def getROC(self, test_labels, predictions, label_headers):
predictions=pd.DataFrame(data=predictions.flatten())
predictions.columns=test_labels.columns.values
if self.type == 'classifier':
test_labels = self.map_str_to_number(test_labels)
fpr, tpr, _ = roc_curve(test_labels, predictions)
plt.figure(1)
plt.plot([0, 1], [0, 1], 'k--')
plt.plot(fpr, tpr)
plt.xlabel('False positive rate')
plt.ylabel('True positive rate')
plt.title('ROC curve')
plt.show()
else:
return 'No Confusion Matrix for Regression'
def getRSquare(self, test_labels, predictions, mode='single'):
df = pd.DataFrame(data=predictions.flatten())
if self.type == 'regressor':
if mode == 'multiple':
errors = r2_score(test_labels, df, multioutput='variance_weighted')
else:
errors = r2_score(test_labels, df)
return errors
else:
return 'No RSquare for Classification'
def getMSE(self, test_labels, predictions):
df = pd.DataFrame(data=predictions.flatten())
if self.type == 'regressor':
errors = mean_squared_error(test_labels, df)
return errors
else:
return 'No MSE for Classification'
def getMAPE(self, test_labels, predictions):
df = pd.DataFrame(data=predictions.flatten())
if self.type == 'regressor':
errors = np.mean(np.abs((test_labels - df.values) / test_labels)) * 100
return errors.values[0]
else:
return 'No MAPE for Classification'
def getRMSE(self, test_labels, predictions):
df = pd.DataFrame(data=predictions.flatten())
if self.type == 'regressor':
errors = sqrt(mean_squared_error(test_labels, df))
return errors
else:
return 'No RMSE for Classification'
plt.ylabel('Residuals')
plt.legend(loc='upper left')
plt.hlines(y=0, xmin=-10, xmax=50, color='black', lw=2)
plt.show()
print('At alpha = 0.1, MSE train: %.3f, test: %.3f' % (mean_squared_error(
y_train, y_train_pred), mean_squared_error(y_test, y_test_pred)))
print('At alpha = 0.1, R^2 train: %.3f, test: %.3f' %
(r2_score(y_train, y_train_pred), r2_score(y_test, y_test_pred)))
## alpha = 0.1 gives the best performing model
## Elastic Net Model
from sklearn.linear_model import ElasticNet
elanet1 = ElasticNet(alpha=1.0, l1_ratio=0.5)
elanet1.fit(X_train, y_train)
y_train_pred = elanet1.predict(X_train)
y_test_pred = elanet1.predict(X_test)
plt.scatter(y_train_pred,
y_train_pred - y_train,
c='green',
marker='o',
edgecolor='white',
label='Training data')
plt.scatter(y_test_pred,
y_test_pred - y_test,
c='red',
marker='s',
edgecolor='white',
label='Test data')
plt.title('Elastic Net Model with alpha = 1')
plt.xlabel('Predicted values')
from sklearn.metrics import r2_score
from sklearn.metrics import mean_squared_error
print('MSE train: %.3f, test: %.3f' % (mean_squared_error(
y_train, y_train_pred), mean_squared_error(y_test, y_test_pred)))
print('R^2 train: %.3f, test: %.3f' %
(r2_score(y_train, y_train_pred), r2_score(y_test, y_test_pred)))
#ElasticNet
from sklearn.linear_model import ElasticNet
for n in floatrange(0.1, 0.5, 5):
elanet = ElasticNet(alpha=n, l1_ratio=0.5)
X = df.iloc[:, :-1].values
y = df['MEDV'].values
elanet.fit(X_train, y_train)
y_train_pred = elanet.predict(X_train)
y_test_pred = elanet.predict(X_test)
#print('MSE train: %.3f, test: %.3f' % (
# mean_squared_error(y_train, y_train_pred),
# mean_squared_error(y_test, y_test_pred)))
#print('R^2 train: %.3f, test: %.3f' % (
# r2_score(y_train, y_train_pred),
# r2_score(y_test, y_test_pred)))
ary = np.array(range(100000))
np.linalg.norm(ary)
sp.linalg.norm(ary)
np.sqrt(np.sum(ary**2))
plt.scatter(y_train_pred,
y_train_pred - y_train,
c='steelblue',
marker='o',
# 定义验证函数
def rmse_cv(model):
rmse = np.sqrt(-cross_val_score(model, X_train, y, scoring="neg_mean_squared_error", cv=5))
return (rmse)
#Lasso
clf1 = LassoCV(alphas=[1, 0.1, 0.001, 0.0005, 0.0003, 0.0002, 5e-4])
clf1.fit(X_train, y)
lasso_preds = np.expm1(clf1.predict(X_test)) # exp(x) - 1 <---->log1p(x)==log(1+x)
score1 = rmse_cv(clf1)
print("\nLasso score: {:.4f} ({:.4f})\n".format(score1.mean(), score1.std()))
#ElasticNet
clf2 = ElasticNet(alpha=0.0005, l1_ratio=0.9)
clf2.fit(X_train, y)
elas_preds = np.expm1(clf2.predict(X_test))
score2 = rmse_cv(clf2)
print("\nElasticNet score: {:.4f} ({:.4f})\n".format(score2.mean(), score2.std()))
# print(lasso_preds)
# print(elas_preds)
# Id_list=[i for i in range(1461,2920)]
# print (len(Id_list))
# price_list=[]
# for i in range(0,1459):
# new_list=[]
# new_list=[Id_list[i],lasso_preds[i]]
# price_list.append(new_list)
# print(price_list)
predictions_ridge = ridge.predict(test_features)
rmse_ridge = sqrt(mean_squared_error(predictions_ridge, test_labels))
print("RMSE:", round(rmse_ridge, 2))
# In[23]:
EN = ElasticNet(alpha=0.01, max_iter=10000, normalize=True, l1_ratio=0.8)
EN.fit(train_features, train_labels)
train_EN = EN.score(train_features, train_labels)
test_EN = EN.score(test_features, test_labels)
coeff_used = np.sum(EN.coef_ != 0)
print("number of features used:", coeff_used)
predictions_EN = EN.predict(test_features)
rmse_EN = sqrt(mean_squared_error(predictions_EN, test_labels))
print("RMSE:", round(rmse_EN, 2))
# In[24]:
df = pd.read_csv("data_clean.csv")
del df["Unnamed: 0"]
df = df[[
"gross_square_feet", "block", "land_square_feet", "lot", "age_of_building",
"borough", "residential_units", "commercial_units", "total_units",
"sale_price"
]]
df['borough'] = df['borough'].astype('category')
from sklearn.linear_model import Lasso
from sklearn.linear_model import Ridge
from sklearn.linear_model import ElasticNet
L = Lasso()
R = Ridge()
EN = ElasticNet()
L.fit(X_train, y_train)
R.fit(X_train, y_train)
EN.fit(X_train, y_train)
y_predL = L.predict(X_test)
y_predR = R.predict(X_test)
y_predEN = EN.predict(X_test)
# Metrics Report
from sklearn.metrics import mean_absolute_error as mae
from sklearn.metrics import mean_squared_error as mse
print("Lasso Mean Absolute Error: ", mae(y_test, y_predL))
print("Lasso Mean Squared Error: ", mse(y_test, y_predL))
print("Lasso Root Mean Squared Error: ", np.sqrt(mse(y_test, y_predL)))
# Lasso Model Checking
if np.sqrt(mse(y_test, y_predL)) < (0.1 * y_mean):
print("ALgo works properly")
else:
print("Model needs some changes")
from sklearn.metrics import mean_absolute_error as mae
from sklearn.cross_validation import KFold
from sklearn.linear_model import LinearRegression, ElasticNet
import numpy as np
from sklearn.datasets import load_boston
boston = load_boston()
x = np.array([np.concatenate((v, [1])) for v in boston.data])
y = boston.target
FIT_EN = False
if FIT_EN:
model = ElasticNet(fit_intercept=True, alpha=0.5)
else:
model = LinearRegression(fit_intercept=True)
model.fit(x, y)
p = np.array([model.predict(xi) for xi in x])
e = p - y
total_error = np.dot(e, e)
rmse_train = np.sqrt(total_error / len(p))
kf = KFold(len(x), n_folds=10)
err = 0
for train, test in kf:
model.fit(x[train], y[train])
p = np.array([model.predict(xi) for xi in x[test]])
e = p - y[test]
err += np.dot(e, e)
rmse_10cv = np.sqrt(err / len(x))
print('RMSE on training: {}'.format(rmse_train))
print('RMSE on 10-fold CV: {}'.format(rmse_10cv))
# print(X_train.shape)
X_train = X_train.reshape((X_train.shape[0], 1))
# print(X_train.shape)
# print(X_test.shape)
X_test = X_test.reshape(X_test.shape[0], 1)
# print(X_test.shape)
regr = ElasticNet(random_state=0)
regr.fit(X_train, y_train)
# print(regr.score(X_train, y_train))
# print(regr.coef_)
# print(regr.intercept_)
y_predicted = regr.predict(X_test)
print('y_test: ')
print(y_test)
print('y_predicted: ')
print(y_predicted)
predictions = list()
for i in range(len(test_scaled)):
X, y = test_scaled[i, 0:-1], test_scaled[i, -1]
yhat = y_predicted[i]
# print("Y_test: " + str(y) + " Yhat: " + str(yhat))
yhat = data_misc.invert_scale(scaler, X, yhat)
# print("yhat no scaled:" + str(yhat))
lasso = Lasso(alpha=5)
ridge = Ridge(alpha=3)
lr = LinearRegression()
dtr = DecisionTreeRegressor(max_depth=17)
bagger = BaggingRegressor(net, verbose = 1)
X_train, X_test, y_train, y_test = train_test_split(X_model, y)
dtr.fit(X_train,y_train)
dtr.score(X_test, y_test)
pred = dtr.predict(X_test)
plt.scatter(y_test, (pred*0.8)-y_test)
net.fit(X_train, y_train)
net.score(X_test, y_test)
preds = net.predict(X_test)
plt.scatter(y_test, (preds) - y_test, alpha = 0.7)
scores = cross_val_score(net, scale(X_model), y, cv=12)
scores.mean()
X2 = pivoted[['compilation_0', 'compilation_1', 'compilation_2']]
y2 = pivoted.compilation_3
X_train, X_test, y_train, y_test = train_test_split(X2, y2, test_size=0.2)
lr.fit(X_train, y_train)
lr.score(X_test, y_test)
pivoted.head()
mapped_pivot = pd.read_csv('pivot_catcherr.csv')
train[val] = train_tmp
test[val] = test_tmp
error_dict = {}
elastic_models = {}
finalError = []
for val in players:
errors2 = []
ENreg = ElasticNet(alpha=0.5, l1_ratio=0.5, normalize=False)
ENreg.fit(train[val]['DEFENSIVE_RATING'].values.reshape(-1, 1),
train[val]['POINTS'])
elastic_models[val] = ENreg
prediction = ENreg.predict(
test[val]['DEFENSIVE_RATING'].values.reshape(-1, 1))
prediction = np.round(prediction, 0)
val_prediction = prediction
val_actual = test[val]['POINTS'].values
cnt = 0
compare = {}
for val1 in prediction:
compare[val1] = test[val]['POINTS'].values[cnt]
cnt += 1
for i in range(len(prediction)):
errors2.append(abs(prediction[i] - test[val]['POINTS'].values[i]))
error_dict[val] = abs(prediction[i] -
test[val]['POINTS'].values[i])
def elastic_net_regression(test, train, seed, alpha, n):
model = ElasticNet(alpha=alpha,
random_state=seed).fit(train.iloc[:, :n], train['loss'])
predicted = model.predict(test.iloc[:, :n])
result = mean_absolute_error(test['loss'], predicted)
print("Elastic Net: " + str(round(result, 2)))
# create an index object of our column names to plot our feature importance with
xCols = xTrain.columns
# now let's plot our coefficients
plt.style.use('ggplot')
plt.plot(range(len(xCols)), elasticNetCoef)
plt.xticks(range(len(xCols)), xCols.values)
plt.title(
"Feature importance of independent variables for\nElasticNet model (coefficient values)"
)
plt.margins(0.02)
plt.show()
# now let's do our 2020 predictions of CPI based on this model
predict2020CPI = model.predict(x2020Forward)
# reset our myData2020Forward index to zero so we can attach these predicted CPIs
myData2020Forward.reset_index(drop=True, inplace=True)
# now let's add this back into our 2020 dataframe
myData2020Forward = pd.concat([
myData2020Forward,
pd.DataFrame(predict2020CPI, columns=['predicted_CPI'])
],
axis=1)
# next we will change the dates from ordinal back to dates so we can union them back together
myData2020Forward['Date'] = myData2020Forward.iloc[:, 0].astype(int).map(
dt.date.fromordinal)
myDataBefore2020['Date'] = myDataBefore2020.iloc[:, 0].astype(int).map(
pred2 = nn_reg.predict(testx)
nn_reg.score(testx, testY)
#Lasso
lasso = Lasso(alpha=1)
lasso.fit(trainx, trainy[y[i]])
pred3 = lasso.predict(testx)
lasso.score(testx, testY)
#Ridge
ridge = Ridge(alpha=1.0)
ridge.fit(trainx, trainy[y[i]])
pred4 = ridge.predict(testx)
ridge.score(testx, testY)
#ElasticNet
elsnet = ElasticNet(alpha=1, l1_ratio=0.7)
elsnet.fit(trainx, trainy[y[i]])
pred5 = elsnet.predict(testx)
elsnet.score(testx, testY)
#plot among them
xx = np.linspace(0, max(testY), 100)
fig = plt.figure(figsize=(10, 8))
ax = plt.gca()
plt.scatter(testY, pred, label='Linear regression')
plt.scatter(testY, pred2, label='$k$-NN')
plt.scatter(testY, pred3, label='Lasso')
plt.scatter(testY, pred4, label='Ridge')
plt.scatter(testY, pred5, label='ElasticNet')
plt.plot(xx, xx)
plt.ylabel('Estimation', fontsize=16)
plt.xlabel('True output', fontsize=16)
plt.legend(fontsize=14)
X = df.iloc[:, 0:13].values
# 正解(目的変数)に住宅価格を設定
y = df["MEDV"].values
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=0)
POLY = PolynomialFeatures(degree=2, include_bias=False)
X_train_pol = POLY.fit_transform(X_train)
X_test_pol = POLY.transform(X_test)
sc = StandardScaler()
X_train_std = sc.fit_transform(X_train_pol)
X_test_std = sc.transform(X_test_pol)
# model = LinearRegression()
# model = Lasso(alpha=0.1)
model = ElasticNet(alpha=0.1, l1_ratio=0.6)
model.fit(X_train_std, y_train)
y_train_pred = model.predict(X_train_std)
y_test_pred = model.predict(X_test_std)
print("MSE train: {0}, test: {1}".format(
mean_squared_error(y_train, y_train_pred),
mean_squared_error(y_test, y_test_pred)))
train_file = train_file.drop(train_file.columns[0], axis=1)
train_file = train_file.values
train_X_temp = train_file[5:50000, :-1]
train_Y = train_file[6:50001, -1]
train_X = np.zeros((train_X_temp.shape[0], 8 * 5))
for i in range(train_X_temp.shape[0]):
for j in range(5):
for k in range(8):
train_X[i][j * 8 + k] = train_X_temp[i - j][k]
test_file_name = dir_path + "test2.csv"
test_file = read_csv(test_file_name, skiprows=1, header=None)
test_file = test_file.values
test_X = np.array(test_file[:, :-1])
test_y = test_file[:, -1]
#best_l1_ratio, best_alpha = train_EN_model(train_X, train_Y, test_X)
#print "Best L1 ratio, Best alpha",best_l1_ratio,best_alpha
#enet = ElasticNet(l1_ratio=best_l1_ratio, alpha=best_alpha)
start = time.time()
enet = ElasticNet()
enet.fit(train_X, train_Y)
#model = "ElasticNet int %.2f coefs %s" % (enet.intercept_, pprint(enet.coef_))
prediction = enet.predict(test_X)
mse = np.mean((prediction - test_y)**2)
print "MSE: ", mse
# print prediction
print "Score: ", enet.score(test_X, test_y)
print "Time: ", (time.time() - start)
def train(in_alpha, in_l1_ratio):
import os
import warnings
import sys
import pandas as pd
import numpy as np
from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
from sklearn.model_selection import train_test_split
from sklearn.linear_model import ElasticNet
import mlflow
import mlflow.sklearn
def eval_metrics(actual, pred):
rmse = np.sqrt(mean_squared_error(actual, pred))
mae = mean_absolute_error(actual, pred)
r2 = r2_score(actual, pred)
return rmse, mae, r2
warnings.filterwarnings("ignore")
np.random.seed(40)
# Read the wine-quality csv file (make sure you're running this from the root of MLflow!)
# Assumes wine-quality.csv is located in the same folder as the notebook
wine_path = "wine-quality.csv"
data = pd.read_csv(wine_path)
# Split the data into training and test sets. (0.75, 0.25) split.
train, test = train_test_split(data)
# The predicted column is "quality" which is a scalar from [3, 9]
train_x = train.drop(["quality"], axis=1)
test_x = test.drop(["quality"], axis=1)
train_y = train[["quality"]]
test_y = test[["quality"]]
# Set default values if no alpha is provided
if float(in_alpha) is None:
alpha = 0.5
else:
alpha = float(in_alpha)
# Set default values if no l1_ratio is provided
if float(in_l1_ratio) is None:
l1_ratio = 0.5
else:
l1_ratio = float(in_l1_ratio)
#mlflow.set_tracking_uri("http://zak-tracking-server-svc-myproject.192.168.64.12.nip.io")
# Useful for multiple runs (only doing one run in this sample notebook)
with mlflow.start_run():
# Execute ElasticNet
lr = ElasticNet(alpha=alpha, l1_ratio=l1_ratio, random_state=42)
lr.fit(train_x, train_y)
# Evaluate Metrics
predicted_qualities = lr.predict(test_x)
(rmse, mae, r2) = eval_metrics(test_y, predicted_qualities)
# Print out metrics
print("Elasticnet model (alpha=%f, l1_ratio=%f):" % (alpha, l1_ratio))
print(" RMSE: %s" % rmse)
print(" MAE: %s" % mae)
print(" R2: %s" % r2)
# Log parameter, metrics, and model to MLflow
mlflow.log_param("alpha", alpha)
mlflow.log_param("l1_ratio", l1_ratio)
mlflow.log_metric("rmse", rmse)
mlflow.log_metric("r2", r2)
mlflow.log_metric("mae", mae)
mlflow.sklearn.log_model(lr, "model")
# Train classifier
clf = ElasticNet()
train = pd.read_csv("train/subtrain.csv", chunksize = 100000, iterator = True)
all_classes = np.array([0, 1])
for chunk in train:
y_train = chunk["click"]
chunk = chunk[cols]
chunk = chunk.join(pd.DataFrame([dayhour(x) for x in chunk.hour], columns=["wd", "hr"]))
chunk.drop(["hour"], axis=1, inplace = True)
Xcat = fh.transform(np.asarray(chunk.astype(str)))
clf.fit(Xcat, y_train)
# Create a submission file
usecols = cols + ["id"]
X_test = pd.read_csv("test/mtest.csv", usecols=usecols)
X_test = X_test.join(pd.DataFrame([dayhour(x) for x in X_test.hour], columns=["wd", "hr"]))
X_test.drop(["hour"], axis=1, inplace = True)
X_enc_test = fh.transform(np.asarray(X_test.astype(str)))
y_act = pd.read_csv("test/mtest.csv", usecols=['click'])
y_pred = clf.predict(X_enc_test)
with open('logloss.txt','a') as f:
f.write('\n'+str(log_loss(y_act, y_pred)))
with open("submission/submission_elnet.csv", "w") as f:
f.write("id,click\n")
for idx, xid in enumerate(X_test.id):
f.write(str(xid) + "," + "{0:.10f}".format(y_pred[idx]) + "\n")
f.close()
df_tmp[list(range(30))] = df_tmp[list(range(30))].where(df_tmp[list(range(30))]>.1,0) topic_0 + topic_7 + topic_8 + topic_9 + topic_12 + topic_14 + topic_16 + topic_17+ topic_20 + topic_23 + topic_24 + topic_25 + topic_28 X = df[[str(x) for x in [0,7,8,9,12,14,16,17,20,23,24,25,28]]+["black_proportion","log_income","log_price","total_RE"]] y = np.where(df['white_proportion']>np.median(df['white_proportion']),1,0) y= df['income'] OLR = OLS(y,X).fit() OLR.summary() OLR.predict(exog=X) df_full_results.params.sort_values() df_results.params.sort_values() df_results.summary() EN = ElasticNet(alpha = .02, l1_ratio=.001) EN.fit(X,y) EN.score(X,y) EN.predict(X) LinR = LinearRegression() LinR.fit(X,y) LinR.score(X,y) RR = Ridge() RR.fit(X,y).score(X,y) pd.Series(RR.coef_) from sklearn.svm import SVR, SVC supportR = SVR() supportR.fit(X,y) supportC = SVC() supportC.fit(X,y) supportC.score(X,y)
def train_and_evaluate(config_path):
config = read_params(config_path)
test_data_path = config["split_data"]["test_path"]
train_data_path = config["split_data"]["train_path"]
random_state = config["base"]["random_state"]
model_dir = config["model_dir"]
alpha = config["estimators"]["ElasticNet"]["params"]["alpha"]
l1_ratio = config["estimators"]["ElasticNet"]["params"]["l1_ratio"]
target = [config["base"]["target_col"]]
train = pd.read_csv(train_data_path, sep=",")
test = pd.read_csv(test_data_path, sep=",")
train_y = train[target]
test_y = test[target]
train_x = train.drop(target, axis=1)
test_x = test.drop(target, axis=1)
lr = ElasticNet(
alpha=alpha,
l1_ratio=l1_ratio,
random_state=random_state)
lr.fit(train_x, train_y)
predicted_qualities = lr.predict(test_x)
(rmse, mae, r2) = eval_metrics(test_y, predicted_qualities)
print("Elasticnet model (alpha=%f, l1_ratio=%f):" % (alpha, l1_ratio))
print(" RMSE: %s" % rmse)
print(" MAE: %s" % mae)
print(" R2: %s" % r2)
#####################################################
scores_file = config["reports"]["scores"]
params_file = config["reports"]["params"]
with open(scores_file, "w") as f:
scores = {
"rmse": rmse,
"mae": mae,
"r2": r2
}
json.dump(scores, f, indent=4)
with open(params_file, "w") as f:
params = {
"alpha": alpha,
"l1_ratio": l1_ratio,
}
json.dump(params, f, indent=4)
#####################################################
os.makedirs(model_dir, exist_ok=True)
model_path = os.path.join(model_dir, "model.joblib")
joblib.dump(lr, model_path)
优化方法呢？
'''
rg = ElasticNet(alpha=1.0,
l1_ratio=0.5,
fit_intercept=True,
normalize=False,
precompute=False,
max_iter=1000,
copy_X=True,
tol=0.0001,
warm_start=False,
positive=False,
random_state=None,
selection='cyclic')
rg.fit(X_train, Y_train)
Y_pre = rg.predict(X_test)
rg.score(X_test, Y_test)
rg.coef_
rg.intercept_
'''
alpha 两个惩罚项系数的相乘，如果是0就是最小二乘了
l1_ratio 混合参数，在[0,1]之间是弹性网的
fit_intercept 是否训练截距
normalize 归一化否
precompute 是否使用Gram矩阵来加速
max_iter 最大迭代次数
copy_X 是否覆盖模型中的X
tol 精度
warm_start 是否使用上一次调用的解决方案作为初始化
positive 设置强制系数为正的嘛？
random_state 随机器
#Random Forest Regressor (good cv, good mape) reg =RR(n_estimators = 100) reg.fit(x_train, y_train) cv_score = cross_val_score(reg,x_train,y_train,cv = 10) cv_score.mean() y_pred = reg.predict(x_test) reg.score(x_test,y_test) forecast_accuracy(y_pred,y_test) #Elastic Net regressor (very bad cv, very good mape) regr = EN(random_state=0) regr.fit(x_train, y_train) cv_score = cross_val_score(regr,x_train,y_train,cv = 10) cv_score.mean() y_pred = regr.predict(x_test) regr.score(x_test,y_test) forecast_accuracy(y_pred,y_test) #K-neighbors Regressor ( bad cv, good mape) regr2 = knr(10) regr2.fit(x_train, y_train) cv_score = cross_val_score(regr2,x_train,y_train,cv = 10) cv_score.mean() y_pred = regr2.predict(x_test) regr2.score(x_test,y_test) forecast_accuracy(y_pred,y_test) #SVR (bad cv, very good mape) regr3 = SVR() regr3.fit(x_train, y_train)
train, test = train_test_split(data)
# The predicted column is "quality" which is a scalar from [3, 9]
train_x = train.drop(["quality"], axis=1)
test_x = test.drop(["quality"], axis=1)
train_y = train[["quality"]]
test_y = test[["quality"]]
alpha = float(sys.argv[1]) if len(sys.argv) > 1 else 0.5
l1_ratio = float(sys.argv[2]) if len(sys.argv) > 2 else 0.5
with mlflow.start_run():
lr = ElasticNet(alpha=alpha, l1_ratio=l1_ratio, random_state=42)
lr.fit(train_x, train_y)
predicted_qualities = lr.predict(test_x)
(rmse, mae, r2) = eval_metrics(test_y, predicted_qualities)
print("Elasticnet model (alpha=%f, l1_ratio=%f):" % (alpha, l1_ratio))
print(" RMSE: %s" % rmse)
print(" MAE: %s" % mae)
print(" R2: %s" % r2)
mlflow.log_param("alpha", alpha)
mlflow.log_param("l1_ratio", l1_ratio)
mlflow.log_metric("rmse", rmse)
mlflow.log_metric("r2", r2)
mlflow.log_metric("mae", mae)
mlflow.sklearn.log_model(lr, "model")
lasso.fit(x_train_all, y_train_all) # training mse y_lasso_train = lasso.predict(x_train_all) lasso_train_mse = mean_squared_error(y_train_all, y_lasso_train) # test mse y_lasso_pred = lasso.predict(x_test) lasso_test_mse = mean_squared_error(y_test, y_lasso_pred) ## elastic net elastic = ElasticNet(alpha = 1.0, l1_ratio=0.5) elastic.fit(x_train_all, y_train_all) # training mse y_elastic_train = elastic.predict(x_train_all) elastic_train_mse = mean_squared_error(y_train_all, y_elastic_train) # test mse y_elastic_pred = elastic.predict(x_test) elastic_test_mse = mean_squared_error(y_test, y_lasso_pred) #### perform cross validation to select model ## ridge regression with CV ridgeCV = RidgeCV(alphas = [0.1, 0.3, 1.0, 3.0, 10.0, 30.0, 100.0, 300.0, 1000.0]) ridgeCV.fit(x_train_all, y_train_all) ridgeCV.alpha_ # training mse y_ridgeCV_train = ridgeCV.predict(x_train_all) ridgeCV_train_mse = mean_squared_error(y_train_all, y_ridgeCV_train)
print X_test.shape
y_train=df_train["Purchase"]
df_train=df_train.drop("Purchase", axis=1)
#from sklearn.feature_selection import SelectKBest
#from sklearn.feature_selection import f_regression
#sel = SelectKBest(f_regression, k=10)
#X_tr=pd.DataFrame(sel.fit_transform(X_train,y_train))
#X_tst=pd.DataFrame(sel.transform(X_test))
#print X_tr.shape
#print X_tst.shape
from sklearn.linear_model import ElasticNet
model=ElasticNet(alpha=0.001)
model.fit(X_train,y_train)
y_pred=model.predict(X_test)
#print y_pred.shape
#print key1.shape
#print key2.shape
out=pd.DataFrame()
out["User_ID"]=key1
out["Product_ID"]=key2
out["Purchase"]=y_pred
out.to_csv('outavb.csv', index=False)
def elastic_net(datapath):
# load mat
datafile = os.path.join(datapath, 'data_numpy.mat')
if os.path.exists(datafile) is False:
print('Data file %s not found.' % datafile)
data_numpy = sio.loadmat(datafile)
# get training and test data
train_x_raw = data_numpy['trainX_raw'];
train_x_smooth= data_numpy['trainX_smooth'];
train_y = data_numpy['trainY'];
test_x_raw = data_numpy['testX_raw'];
test_x_smooth = data_numpy['testX_smooth'];
test_y = data_numpy['testY'];
base_y = data_numpy['baseY'];
train_y = train_y.ravel()
t_start = time.perf_counter()
x_fft = np.fft.fft(train_x_raw)
raw_fft_time = time.perf_counter() - t_start
train_x_raw_fft = np.concatenate((np.imag(x_fft), np.real(x_fft)), axis=1)
x_fft = np.fft.fft(test_x_raw)
test_x_raw_fft = np.concatenate((np.imag(x_fft), np.real(x_fft)), axis=1)
t_start = time.perf_counter()
x_fft = np.fft.fft(train_x_smooth)
smooth_fft_time = time.perf_counter() - t_start
train_x_smooth_fft = np.concatenate((np.imag(x_fft), np.real(x_fft)), axis=1)
x_fft = np.fft.fft(test_x_smooth)
test_x_smooth_fft = np.concatenate((np.imag(x_fft), np.real(x_fft)), axis=1)
enet_raw = ElasticNet(alpha=0.5, max_iter=50000, tol=0.3)
t_start = time.perf_counter()
enet_raw.fit(train_x_raw, train_y)
elastic_net_raw_time = time.perf_counter() - t_start
pred_y = enet_raw.predict(test_x_raw)
np.savetxt(os.path.join(datapath, 'elastic_net_raw.txt'), pred_y)
enet_raw_fft = ElasticNet(alpha=0.5, max_iter=50000, tol=0.3)
t_start = time.perf_counter()
enet_raw_fft.fit(train_x_raw_fft, train_y)
elastic_net_raw_fft_time = time.perf_counter() - t_start
pred_y = enet_raw_fft.predict(test_x_raw_fft)
np.savetxt(os.path.join(datapath, 'elastic_net_raw_fft.txt'), pred_y)
enet_smooth = ElasticNet(alpha=0.5, max_iter=50000, tol=0.3)
t_start = time.perf_counter()
enet_smooth.fit(train_x_smooth, train_y)
elastic_net_smooth_time = time.perf_counter() - t_start
pred_y = enet_smooth.predict(test_x_smooth)
np.savetxt(os.path.join(datapath, 'elastic_net_smooth.txt'), pred_y)
enet_smooth_fft = ElasticNet(alpha=0.5, max_iter=50000, tol=0.3)
t_start = time.perf_counter()
enet_smooth_fft.fit(train_x_smooth_fft, train_y)
elastic_net_smooth_fft_time = time.perf_counter() - t_start
pred_y = enet_smooth_fft.predict(test_x_smooth_fft)
np.savetxt(os.path.join(datapath, 'elastic_net_smooth_fft.txt'), pred_y)
f_time = open(os.path.join(datapath, 'elastic_net_time.txt'), 'w')
f_time.write(str(raw_fft_time) + '\n')
f_time.write(str(smooth_fft_time)+ '\n')
f_time.write(str(elastic_net_raw_time)+ '\n')
f_time.write(str(elastic_net_raw_fft_time)+ '\n')
f_time.write(str(elastic_net_smooth_time)+ '\n')
f_time.write(str(elastic_net_smooth_fft_time)+ '\n')
f_time.close()
flag = False
for i in range(20):
X, y = 0, 0
if (flag):
diff_values = data_misc.difference(raw_values, 1)
supervised = data_misc.timeseries_to_supervised(diff_values, 1)
supervised_values = supervised.values
train, test = supervised_values[0:-1], supervised_values[-1:]
test_scaled = scaler.transform(test)
X, y = test_scaled[0, 0:-1], test_scaled[0, -1]
else:
flag = True
X, y = test_scaled[i, 0:-1], test_scaled[i, -1]
yhat = regr.predict([X])
print("Y_test: " + str(y) + " Yhat: " + str(yhat))
yhat = data_misc.invert_scale(scaler, X, yhat)
# Se recorre -1 porque para que no se alinie donde empezó
yhat = data_misc.inverse_difference(raw_values, yhat, -1 - i)
# store forecast
predictions.append(yhat)
allList.append(yhat)
# df = DataFrame(raw_values)
# print(df[0][i])
# columns = [df[0][i] for i in range(0,df.size)]
# columns.append(yhat)
raw_values = allList
# ElasticNet Regression import numpy as np from sklearn import datasets from sklearn.linear_model import ElasticNet # load the diabetes datasets dataset = datasets.load_diabetes() # fit a model to the data model = ElasticNet(alpha=0.1) model.fit(dataset.data, dataset.target) print(model) # make predictions expected = dataset.target predicted = model.predict(dataset.data) # summarize the fit of the model mse = np.mean((predicted-expected)**2) print(mse) print(model.score(dataset.data, dataset.target))
def stacking(ext_total_df):
cat_col = [15, 18]
lin_col = [3, 9, 10, 11, 14, 17, 21, 22, 23, 24, 25] + list(range(
27, 81)) + list(range(82, 108)) # ここまで欠損値無し？
nan_is_m1 = [
"home_team_match_point_prev3_mean", "home_team_match_point_prev5_mean",
"away_team_match_point_prev3_mean", "away_team_match_point_prev5_mean"
]
lin_total_df = ext_total_df.iloc[:, [0] + lin_col]
lin_total_df = pd.concat([
lin_total_df,
pd.get_dummies(ext_total_df.iloc[:, cat_col].astype("str"),
drop_first=True)
],
axis=1)
lin_total_df.loc[:,
nan_is_m1] = lin_total_df.loc[:,
nan_is_m1].replace(-1, 1.2)
dropcol = ["attendance"]
all_train_X = lin_total_df.query("1994 <= match_date_year").drop(dropcol,
axis=1)
all_train_y = np.log1p(
lin_total_df.query("1994 <= match_date_year")["attendance"])
all_train_y2 = lin_total_df.query(
"1994 <= match_date_year")["attendance"] / lin_total_df.query(
"1994 <= match_date_year")["capacity"]
for year in tqdm(range(2002, 2017, 2)):
window = 6
duration = 2
Z = all_train_X.match_date_year
Z2 = all_train_X.division
train = (year - duration - window < Z) & (Z <= year - duration)
val = (year - duration < Z) & (Z <= year)
train_X = all_train_X.loc[train, :]
train_y = all_train_y[train]
train_y2 = all_train_y2[train]
val_X = all_train_X.loc[val, :]
scl = StandardScaler()
scl.fit(train_X.values.astype(np.float64))
train_scl = scl.transform(train_X.values.astype(np.float64))
val_scl = scl.transform(val_X.values.astype(np.float64))
elastic_net = ElasticNet(alpha=10**-2.7,
l1_ratio=0.75,
max_iter=10000,
random_state=2434)
elastic_net.fit(train_scl, train_y2)
ext_total_df.loc[val_X.index,
"elastic_net"] = elastic_net.predict(val_scl).clip(
0, 1)
train = (2010 < Z) & (Z <= 2016)
val = (2017 == Z) | ((Z == 2018) & ((all_train_X["section"] <= 17) |
(33 <= all_train_X["section"])))
train_X = all_train_X.loc[train, :]
train_y = all_train_y[train]
train_y2 = all_train_y2[train]
val_X = all_train_X.loc[val, :]
scl = StandardScaler()
scl.fit(train_X.values.astype(np.float64))
train_scl = scl.transform(train_X.values.astype(np.float64))
val_scl = scl.transform(val_X.values.astype(np.float64))
elastic_net = ElasticNet(alpha=10**-2.7, l1_ratio=0.75, random_state=2434)
elastic_net.fit(train_scl, train_y2)
ext_total_df.loc[val_X.index,
"elastic_net"] = elastic_net.predict(val_scl).clip(0, 1)
return ext_total_df
def elasticnet():
regressor = ElasticNet(alpha=1, l1_ratio=0.5, normalize=False)
regressor.fit(X_train, y_train)
y_predictions = regressor.predict(X_test)
return (regressor.score(X_test, y_test),
sqrt(mean_squared_error(y_test, y_predictions)))
y_test_pred_ridge = ridge_regressor.predict(X_test)
print('MSE train Ridge: %.3f, test: %.3f' %
(mean_squared_error(y_train, y_train_pred_ridge),
mean_squared_error(y_test, y_test_pred_ridge)))
print('R^2 train Ridge: %.3f, test: %.3f' % (r2_score(
y_train, y_train_pred_ridge), r2_score(y_test, y_test_pred_ridge)))
lasso_regressor.fit(X_train, y_train)
y_train_pred_lasso = lasso_regressor.predict(X_train)
y_test_pred_lasso = lasso_regressor.predict(X_test)
print('MSE train Lasso: %.3f, test: %.3f' %
(mean_squared_error(y_train, y_train_pred_lasso),
mean_squared_error(y_test, y_test_pred_lasso)))
print('R^2 train Lasso: %.3f, test: %.3f' % (r2_score(
y_train, y_train_pred_lasso), r2_score(y_test, y_test_pred_lasso)))
elastic_regressor.fit(X_train, y_train)
y_train_pred_elastic = elastic_regressor.predict(X_train)
y_test_pred_elastic = elastic_regressor.predict(X_test)
print('MSE train elastic: %.3f, test: %.3f' %
(mean_squared_error(y_train, y_train_pred_elastic),
mean_squared_error(y_test, y_test_pred_elastic)))
print('R^2 train elastic: %.3f, test: %.3f' % (r2_score(
y_train, y_train_pred_elastic), r2_score(y_test, y_test_pred_elastic)))
# Now let's do a Random Forest Regression
# In[15]:
from sklearn.ensemble import RandomForestRegressor
forest = RandomForestRegressor(n_estimators=1000,
criterion='mse',
random_state=1,
n_jobs=-1)
forest.fit(X_train, y_train)
y_train_pred = forest.predict(X_train)
import numpy as np
from sklearn.datasets import load_svmlight_file
from sklearn.cross_validation import KFold
from sklearn.linear_model import ElasticNet, LinearRegression
data, target = load_svmlight_file('data/E2006.train')
# Edit the lines below if you want to switch method:
# met = LinearRegression(fit_intercept=True)
met = ElasticNet(fit_intercept=True, alpha=.1)
kf = KFold(len(target), n_folds=10)
err = 0
for train, test in kf:
met.fit(data[train], target[train])
p = met.predict(data[test])
p = np.array(p).ravel()
e = p - target[test]
err += np.dot(e, e)
rmse_10cv = np.sqrt(err / len(target))
met.fit(data, target)
p = met.predict(data)
p = p.ravel()
e = p - target
total_error = np.dot(e, e)
rmse_train = np.sqrt(total_error / len(p))
gs_cv_lasso.best_params_
lasso_tuned = Lasso(**gs_cv_lasso.best_params_).fit(X_train, y_train)
y_pred = lasso_tuned.predict(X_test)
np.sqrt(mean_squared_error(y_test, y_pred))
pd.Series(lasso_tuned.coef_, index=X_train.columns)
# ElasticNet REGRESSION
df = load_advertising()
X = df.drop('sales', axis=1)
y = df[["sales"]]
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.20,
random_state=46)
enet_model = ElasticNet().fit(X_train, y_train)
y_pred = enet_model.predict(X_test)
np.sqrt(mean_squared_error(y_test, y_pred))
# MODEL TUNING WITH GRIDSEARCHCV
enet_params = {
"l1_ratio": [0.1, 0.4, 0.5, 0.6, 0.8, 1],
"alpha": [0.1, 0.01, 0.001, 0.2, 0.3, 0.5, 0.8, 0.9, 1]
}
enet_model = ElasticNet()
gs_cv_enet = GridSearchCV(enet_model, enet_params, cv=10).fit(X_train, y_train)
gs_cv_enet.best_params_
enet_tuned = ElasticNet(**gs_cv_enet.best_params_).fit(X_train, y_train)
print("Took {:0.4g}s to compute training Fastfood expansion.".format(elapsed_ff_kern_train))
st = time()
PHI_valid, _ = FastfoodForKernel(validationData, para, sgm)
elapsed_ff_kern_valid = time() - st
print("Took {:0.4g}s to compute validation Fastfood expansion.".format(elapsed_ff_kern_valid))
# Train elastic net on projected training data
en = ElasticNet()
st = time()
en.fit(PHI_train.T, trainLabels)
elapsed_en_fit = time() - st
print("Took {:0.4g}s to fit elastic net on projected training data.".format(elapsed_en_fit))
# Predict labels for projected validation data
st = time()
y_pred = en.predict(PHI_valid.T)
elapsed_en_pred = time() - st
print("Took {:0.4g}s to predict on projected validation data.".format(elapsed_en_pred))
# Report performance
mse_proj = metrics.mean_squared_error(validationLabels, y_pred)
print("For projected data, MSE = {:0.4g}.".format(mse_proj))
# Train elastic net on original training data
en = ElasticNet()
st = time()
en.fit(trainData.T, trainLabels)
elapsed_en_fit = time() - st
print("Took {:0.4g}s to fit elastic net on original training data.".format(elapsed_en_fit))
# Predict labels for original validation data
elasticnet = ElasticNet()
elasticnet.fit(X_train, y_train)
# In[1385]:
elasticnet_score = elasticnet.score(X_test, y_test)
elasticnet_score
# In[1420]:
elasticnet_score = elasticnet.score(X_test, y_test)
elasticnet_score
# In[1386]:
elasticnet_pred = elasticnet.predict(X_test)
# In[1422]:
# The mean squared error
print("Root mean squared error: %.2f" %
sqrt(mean_squared_error(y_test, elasticnet_pred)))
# The absolute squared error
print("Mean absolute error: %.2f" %
mean_absolute_error(y_test, elasticnet_pred))
# Explained variance score: 1 is perfect prediction
print('R-squared: %.2f' % r2_score(y_test, elasticnet_pred))
# In[1416]:
#Evaluate Models
print ridge_scores.mean()
print ridge_scores
# combination of ridge and Lasso
print "Elastic net regularization"
for alpha in range(1,5):
elastic_net = ElasticNet(alpha)
elastic_net_scores =cross_val_score(elastic_net, x, y, cv = 5)
print "alpha={a}".format(a=alpha)
print elastic_net_scores.mean()
print elastic_net_scores
# best performing regressor for this data set was Elastic net with alpha=1
# with score = 0.472705248975
# draw scatter plot for values predicted with this regressor
print "Showing scatter plot for elastic net with alpha = 1"
elastic_net = ElasticNet(1)
elastic_net.fit(x, y)
predicted_y = elastic_net.predict(x)
fig = plt.figure()
plt.scatter(y, predicted_y, alpha=0.3, )
fig.suptitle('Boston real estate pricing', fontsize=20)
plt.figtext(.5,.9,'Elastic net regularization, alpha=1', fontsize=15, ha='center')
plt.xlabel('Actual value, $1000s', fontsize=18)
plt.ylabel('Predicted value, $1000s', fontsize=18)
plt.show()
sc_x = StandardScaler()
sc_y = StandardScaler()
X_std = sc_x.fit_transform(X)
y_std = np.ravel(sc_y.fit_transform(y.reshape(-1, 1)))
X_train, X_test, y_train, y_test = train_test_split(
X_std, y_std, test_size=0.3, random_state=0)
# train and test
from sklearn.linear_model import ElasticNet
from sklearn.metrics import mean_squared_error
alphas = [0.001, 0.01, 0.1, 1, 10, 100, 1000]
train_errors = []
test_errors = []
for alpha in alphas:
model = ElasticNet(alpha=alpha, l1_ratio=0.5)
model.fit(X_train, y_train)
y_train_pred = model.predict(X_train)
y_test_pred = model.predict(X_test)
train_errors.append(mean_squared_error(y_train, y_train_pred))
test_errors.append(mean_squared_error(y_test, y_test_pred))
print(train_errors)
print(test_errors)
class linReg:
def __init__(self, in_df):
df = self.__imputeVals(in_df.copy())
self.X = df.drop(columns=["SalePrice"]).copy()
self.y = np.log(df.SalePrice.values.reshape(-1, 1))
self._gridSearch = None
self.pipeline_X = self.__make_pipe()
self.pipeline_y = StandardScaler()
self._searchSpace = None
self._params = None
self.lm = ElasticNet()
def __imputeVals(self, in_df):
return imputeVals(in_df)
def __make_pipe(self):
nonePipeline = make_pipeline(
SimpleImputer(strategy="constant", fill_value="None"),
OneHotEncoder(drop="first"))
zeroPipeline = make_pipeline(
SimpleImputer(strategy="constant", fill_value=0),
OneHotEncoder(drop="first", categories="auto"))
scalePipeline = make_pipeline(
SimpleImputer(strategy="constant", fill_value=0), StandardScaler())
regressionPipeline = ColumnTransformer(
[("setNone", nonePipeline, fillNone),
("setZero", zeroPipeline, fillZeroCat),
("transformed", scalePipeline, fillZeroCont),
("dictImputed",
make_pipeline(dictImputer(imputeDict), OneHotEncoder(
drop="first")), list(imputeDict.keys())),
("bool", "passthrough", imputeBool),
("categoricalInts", "passthrough", cat_to_int),
("dropped", "drop", dropList)],
remainder="drop")
return regressionPipeline
def gridSearch(self, params, cv=5, njobs=-1, verbose=50):
self._searchSpace = params
#self._params = None
piped_X = self.pipeline_X.fit_transform(self.X)
piped_y = self.pipeline_y.fit_transform(self.y)
self._gridSearch = GridSearchCV(self.lm,
params,
cv=cv,
scoring="neg_mean_squared_error",
n_jobs=njobs,
verbose=verbose)
self._gridSearch.fit(piped_X, piped_y)
def getBestParams(self):
if self._gridSearch is not None:
return self._gridSearch.best_params_
else:
raise ValueError()
def getBestScore(self):
if self._gridSearch is not None:
return self._gridSearch.best_score_
else:
raise ValueError()
def fitModel(self, params):
piped_X = self.pipeline_X.fit_transform(self.X)
piped_y = self.pipeline_y.fit_transform(self.y)
self._params = params
self.lm.set_params(**params)
self.lm.fit(piped_X, piped_y)
def __invert(self, y):
return np.exp(self.pipeline_y.inverse_transform(y))
def getTrainScore(self):
piped_X = self.pipeline_X.transform(self.X)
piped_y = self.pipeline_y.transform(self.y)
return self.lm.score(piped_X, piped_y)
# Root Mean Square Log Error
def getRMSLE(self):
piped_X = self.pipeline_X.transform(self.X)
preds = self.pipeline_y.inverse_transform(self.lm.predict(piped_X))
return mean_squared_error(self.y, preds)
def predict(self, test_X):
piped_X = self.pipeline_X.transform(self.__imputeVals(test_X))
preds = self.lm.predict(piped_X)
return self.__invert(preds)
from sklearn.linear_model import ElasticNetCV, ElasticNet
from sklearn.metrics import mean_squared_error, r2_score
from matplotlib import pyplot as plt
data, target = load_svmlight_file('data/E2006.train')
# 다음을 변경한다
# from sklearn.linear_model import Lasso
# met = Lasso(alpha=0.1)
met = ElasticNet(alpha=0.1)
kf = KFold(len(target), n_folds=5)
pred = np.zeros_like(target)
for train, test in kf:
met.fit(data[train], target[train])
pred[test] = met.predict(data[test])
print('[EN 0.1] RMSE on testing (5 fold), {:.2}'.format(np.sqrt(mean_squared_error(target, pred))))
print('[EN 0.1] R2 on testing (5 fold), {:.2}'.format(r2_score(target, pred)))
print('')
# ElasticNetCV 생성자(모든 CPU 사용)
met = ElasticNetCV(n_jobs=-1)
kf = KFold(len(target), n_folds=5)
pred = np.zeros_like(target)
for train, test in kf:
met.fit(data[train], target[train])
pred[test] = met.predict(data[test])
print('[EN CV] RMSE on testing (5 fold), {:.2}'.format(np.sqrt(mean_squared_error(target, pred))))
std = X_train.std(axis=0)
mean = X_train.mean(axis=0)
X_train = (X_train - mean) / std
X_test = (X_test - mean) / std
std = y_train.std(axis=0)
mean = y_train.mean(axis=0)
y_train = (y_train - mean) / std
y_test = (y_test - mean) / std
gc.collect()
print("- benching ElasticNet")
clf = ElasticNet(alpha=alpha, rho=0.5, fit_intercept=False)
tstart = time()
clf.fit(X_train, y_train)
elnet_results[i, j, 0] = mean_squared_error(clf.predict(X_test),
y_test)
elnet_results[i, j, 1] = time() - tstart
gc.collect()
print("- benching SGD")
n_iter = np.ceil(10 ** 4.0 / n_train)
clf = SGDRegressor(alpha=alpha, fit_intercept=False,
n_iter=n_iter, learning_rate="invscaling",
eta0=.01, power_t=0.25)
tstart = time()
clf.fit(X_train, y_train)
sgd_results[i, j, 0] = mean_squared_error(clf.predict(X_test),
y_test)
sgd_results[i, j, 1] = time() - tstart
class RiskClassifier():
def __init__(self, train=False):
if train:
self.train()
#else:
#Load classifier
def train(self, plot=False):
X, y = self.prepareData()
n_samples = X.shape[0]
X_train, y_train = X[:n_samples // 2], y[:n_samples // 2]
X_test, y_test = X[n_samples // 2:], y[n_samples // 2:]
#######################################################################
# Lasso
alpha = 0.1
self.lasso = Lasso(alpha=alpha)
y_pred_lasso = self.lasso.fit(X_train, y_train).predict(X_test)
r2_score_lasso = r2_score(y_test, y_pred_lasso)
print(self.lasso)
print("r^2 on test data : %f" % r2_score_lasso)
# #####################################################################
# ElasticNet
from sklearn.linear_model import ElasticNet
self.enet = ElasticNet(alpha=alpha, l1_ratio=0.7)
y_pred_enet = self.enet.fit(X_train, y_train).predict(X_test)
r2_score_enet = r2_score(y_test, y_pred_enet)
print(self.enet)
print("r^2 on test data : %f" % r2_score_enet)
if plot:
import matplotlib.pyplot as plt
plt.plot(self.enet.coef_, color='lightgreen', linewidth=2, \
label='Elastic net coefficients')
plt.plot(self.lasso.coef_, color='gold', linewidth=2, \
label='Lasso coefficients')
plt.legend(loc='best')
plt.title("Lasso R^2: %f, Elastic Net R^2: %f" %
(r2_score_lasso, r2_score_enet))
plt.show()
def classify(self, example, test=None):
#perform the classification
y_pred_lasso = self.lasso.predict(example)
y_pred_enet = self.enet.predict(example)
if not test is None:
r2_score_lasso = r2_score(test, y_pred_lasso)
r2_score_enet = r2_score(test, y_pred_enet)
print("r^2 Classify Lasso test: %f" % r2_score_lasso)
print("r^2 Classify Enet test: %f" % r2_score_enet)
return y_pred_lasso, y_pred_enet
def getAllData(self):
dfCorruption = pd.read_csv('../economy/Corruption.csv',
sep=';',
na_values=0)
dfEducation = pd.read_csv('../economy/Education.csv',
sep=';',
na_values=0)
dfGini = pd.read_csv('../economy/Gini.csv', sep=';', na_values=0)
dfImports = pd.read_csv('../economy/Imports.csv', sep=';', na_values=0)
dfInflation = pd.read_csv('../economy/Inflation.csv',
sep=';',
na_values=0)
dfPopulation = pd.read_csv('../economy/Population.csv',
sep=';',
na_values=0)
dfReserves = pd.read_csv('../economy/Reserves.csv',
sep=';',
na_values=0)
dfUnemployment = pd.read_csv('../economy/Unemployment.csv',
sep=';',
na_values=0)
riskData = pd.read_csv('../targets/psr.csv', na_values=0)
# result = pd.concat([dfCorruption, dfEducation, dfGini, dfImports, dfInflation, dfPopulation, dfReserves, dfUnemployment], axis=1, join='inner')
allData = dfCorruption.set_index('Country Name') \
.join(dfEducation.set_index('Country Name'), lsuffix='_corruption') \
.join(dfGini.set_index('Country Name'), lsuffix='_education') \
.join(dfImports.set_index('Country Name'),lsuffix='_gini') \
.join(dfInflation.set_index('Country Name'),lsuffix='_imports') \
.join(dfPopulation.set_index('Country Name'), lsuffix = '_inflation') \
.join(dfReserves.set_index('Country Name'), lsuffix = '_population') \
.join(dfUnemployment.set_index('Country Name'), lsuffix = '_reserves', rsuffix = '_unemployment')
allData = allData.join(riskData.set_index('Country Name'), how='inner')
return allData
def getDataFromYear(self, year):
allData = self.getAllData()
strYear = str(year)
data = allData[[
strYear + '_corruption', strYear + '_education', strYear + '_gini',
strYear + '_imports', strYear + '_inflation',
strYear + '_population', strYear + '_reserves',
strYear + '_unemployment'
]].fillna(0)
risk = allData[[strYear+'_PRS'+strYear[2:]+'VA', \
strYear+'_PRS'+strYear[2:]+'PV', \
strYear+'_PRS'+strYear[2:]+'GE', \
strYear+'_PRS'+strYear[2:]+'RQ', \
strYear+'_PRS'+strYear[2:]+'RL', \
strYear+'_PRS'+strYear[2:]+'CC']].fillna(0)
return data, risk
def prepareData(self):
# Someday we will have more data so we'll load more years
# into our classifier
data2016, risk2016 = self.getDataFromYear(2016)
X = data2016.as_matrix()
y = risk2016['2016_PRS16PV'].as_matrix()
return X, y
