def interactor(df):
""" This function takes in a data frame and creates binary interaction
terms from all numerical and categorical variables as well as the assessment
questions, and outputs a data frame """
my_data_complete = df.dropna()
# interactions can only be done for non-missings
colnames = list(my_data_complete.columns.values)
# id and date columns
id_cols_list = [
x
for x in colnames # only for continuous vars
if not (bool(re.search("_N$", x)) | bool(re.search("_C$", x)) | bool(re.search("_Q$", x)))
]
# actual feature columns - to make interactions from
new_cols_list = [
x
for x in colnames # only for continuous vars
if (bool(re.search("_N$", x)) | bool(re.search("_C$", x)) | bool(re.search("_Q$", x)))
]
othervars = my_data_complete[id_cols_list]
little_df = my_data_complete[new_cols_list]
# computing all binary interaction terms
poly = PolynomialFeatures(degree=2, interaction_only=True)
theints = pd.DataFrame(poly.fit_transform(little_df))
theints = theints.drop(theints.columns[0], axis=1) # dropping the first column
theints.columns = list(new_cols_list + list(itertools.combinations(new_cols_list, 2)))
# concatenating the interaction terms to the original data frame
df = pd.DataFrame(othervars.join(theints))
new_features = theints.columns.values
return df, new_features
def learning_curve(classifier, X, y, cv, sample_sizes,
degree=1, pickle_path=None, verbose=True):
""" Learning curve
"""
learning_curves = []
for i, (train_index, test_index) in enumerate(cv):
X_train = X[train_index]
X_test = X[test_index]
y_train = y[train_index]
y_test = y[test_index]
if degree > 1:
poly = PolynomialFeatures(degree=degree, interaction_only=False, include_bias=True)
X_train = poly.fit_transform(X_train)
X_test = poly.transform(X_test)
lc = []
for sample in sample_sizes:
classifier.fit(X_train[:sample], y_train[:sample])
# apply classifier on test set
y_pred = classifier.predict(X_test)
confusion = metrics.confusion_matrix(y_test, y_pred)
lc.append(balanced_accuracy_expected(confusion))
learning_curves.append(lc)
if verbose: print(i, end=' ')
# pickle learning curve
if pickle_path:
with open(pickle_path, 'wb') as f:
pickle.dump(learning_curves, f, protocol=4)
if verbose: print()
def load_data(datafile = DEFAULT_DATA_FILE):
"""
Loads feature and classification data from the given file.
Returns a tuple of (features, labels) where both are
features is an NP array and labels is a list.
"""
# Read data
dataframe = pd.read_csv(datafile)
views = [ float(x) for x in dataframe["views"].tolist()]
favs = [ float(x) for x in dataframe["favorites"].tolist()]
ratio = []
for i in range(len(views)):
ratio.append(favs[i] / views[i])
ratio = cap_results(ratio)
# Uncomment this and fix the return line if you want to do
# favorites prediction instead
# favs = dataframe["favorites"].tolist()
# 5 is the first column after 'favs'.
# -1 means last column from the end, because I added an extra
# column for the artist name, which we want to ignore.
dataframe = dataframe.drop("artist", axis=1)
dataframe = dataframe.iloc[:, 5:]
features = dataframe.values
# # interaction terms
poly = PolynomialFeatures(interaction_only=True)
features = poly.fit_transform(features)
print "interaction"
return features, ratio, dataframe.columns.values
def main():
weekfile = sys.argv[1]
modelfile = sys.argv[2]
polyorder = int(sys.argv[3])
metadata = sys.argv[4]
week_data = np.genfromtxt(weekfile, delimiter=',', skip_header=1)
poly = PolynomialFeatures(degree=polyorder)
Xpoly = poly.fit_transform(week_data)
with open(modelfile, 'rb') as model, open(metadata) as md:
lr = pickle.load(model)
preds = lr.predict(Xpoly).astype(int)
probs = lr.predict_proba(Xpoly)
results = []
for i, line in enumerate(md):
home, away = line.strip().split(',')
if preds[i] == 1:
results.append((home+'*', "{0:.3f}".format(probs[i,1]), away, "{0:.3f}".format(probs[i,0])))
else:
results.append((away, "{0:.3f}".format(probs[i,0]), home+'*', "{0:.3f}".format(probs[i,1])))
results = sorted(results, key=getWinnerProb, reverse=True)
for result in results:
print('\t'.join(result))
def predict(self, x):
## as it is trained on polynominal features, we need to transform x
poly = PolynomialFeatures(degree=self.degree)
polynominal_features = poly.fit_transform(x)[0]
print polynominal_features.reshape
return self.model.predict(polynominal_features)
def lassoRegression(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)
### ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ###
lassoRegression = Lasso(alpha=1e-7)
lassoRegression.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 = lassoRegression.predict(scaled_dummyXp)
outputFILE = 'plot-lassoRegression.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 computeZs(w, x_train):
z = []
for i in xrange(x_train.shape[0]):
z.append(np.array([sigmoid(w[j], x_train[i]) for j in xrange(w.shape[0])]))
poly = PolynomialFeatures(1)
z = poly.fit_transform(z)
return np.array(z)
def log_reg_kclass(x, y, nfolds=4, degree=1, limit=None):
"""Performs logistic regression experiments on Iris dataset for k class discrimination."""
#print 'Training k Class classifier on Iris dataset'
if limit is not None:
print 'Considering only', limit, ' datapoints'
x = x[:limit]
y = y[:limit]
#x /= x.max(axis=0)
poly = PolynomialFeatures(degree)
x = poly.fit_transform(x)
num_classes = len(set(y))
avg_accuracy = 0.; avg_precision = np.zeros(num_classes); avg_recall = np.zeros(num_classes); avg_fscore = np.zeros(num_classes); avg_conf_mat = np.zeros([num_classes, num_classes])
kf = KFold(y.shape[0], n_folds=nfolds, shuffle=True)
for train_ids, test_ids in kf:
thetas = log_reg_trainer_kclass(x[train_ids], y[train_ids])
y_pred = log_reg_pred_kclass(thetas, x[test_ids])
acc = accuracy_score(y[test_ids], y_pred)
avg_accuracy += acc
precision1, recall1, fscore1, supp1 = precision_recall_fscore_support(y[test_ids], y_pred)
conf_mat = confusion_matrix(y[test_ids], y_pred)
avg_precision += precision1; avg_recall += recall1; avg_fscore += fscore1; avg_conf_mat += conf_mat
lol=0
return avg_accuracy / nfolds, avg_precision / nfolds, avg_recall / nfolds, avg_fscore / nfolds, avg_conf_mat / nfolds
def get_cl(tau, consider='EE', degree=5):
if consider == 'EE':
values = values_EE
else:
values = values_BB
v = values#[:100]
p = points#[:100]
poly = PolynomialFeatures(degree=degree)
# Vandermonde matrix of pre-computed paramter values.
X_ = poly.fit_transform(p.reshape(-1,1))
predict = np.array([tau]).reshape(1,-1)
# Creates matrix of values you want to estimate from the existing
# measurements. Computation speed scales very slowly when you ask for
# estimate of many sets of parameters.
predict_ = poly.fit_transform(predict)
clf = LinearRegression()
estimate = []
for l in range(2, v.shape[1]):
values_l = v[:,l]
clf.fit(X_, values_l)
estimate_l = clf.predict(predict_)
estimate.append(estimate_l)
estimate = np.array(estimate)
ell = np.arange(2, l+1)
Z = 2*np.pi/(ell*(ell+1))
return ell, Z*estimate[:,0]
def polynomial_expansion(self, rank=2): """ Expand the features with polynonial of rank rnank """ pf = PolynomialFeatures(degree=2) self.X_red = pf.fit_transform(self.X_red) self.X_white = pf.fit_transform(self.X_white)
def test_polynomial_fits(x, y, n_comps, model, k_folds=3):
for i in range(1,6):
poly = PolynomialFeatures(degree=i)
poly_x = poly.fit_transform(x)
r2_mean, r2_std, mse_mean, mse_std = run_conventional_linkage(poly_x, y, n_comps, model)
print r2_mean, r2_std, mse_mean, mse_std
print
def main():
testfile = sys.argv[1]
modelfile = sys.argv[2]
polyorder = int(sys.argv[3])
testweeks = sys.argv[4]
test_data = np.genfromtxt(testfile, delimiter=',', skip_header=1)
X = test_data[:,:-1]
y = test_data[:,-1]
poly = PolynomialFeatures(degree=polyorder)
Xpoly = poly.fit_transform(X)
with open(modelfile, 'rb') as model, open(testweeks) as weeks:
lr = pickle.load(model)
games_per_week = (int(line) for line in weeks)
ranges = []
pos = 0
for week in games_per_week:
newpos = pos + week
ranges.append( (pos, newpos) )
pos = newpos
print('W\tL\tPoints')
weekly_results = (evaluate_week(week, Xpoly, y, lr) for week in ranges)
for result in weekly_results:
print('\t'.join(str(piece) for piece in result))
def newtonRaphson(inputFiles):
pol = PolynomialFeatures(2)
errors = []
for File in inputFiles:
data = tools.readData(File)
X = data[:, :-1]
Y = data[:, -1]
kf = KFold(len(Y), n_folds = 10)
trainError = 0
testError = 0
for train, test in kf:
Z = pol.fit_transform(X[train])
row, col = Z.shape
theta = np.empty(col, dtype='float')
meanDiff = 1.0
i = 1
#print "Theta iteration %s: \n%s" % ('0', str(theta))
while abs(meanDiff) > 1.0e-15 :
theta_new = recalculateTheta(theta, Z, Y[train])
diff = np.subtract(theta_new, theta)
meanDiff = np.mean(diff)
#print "Theta iteration %s: \n%s" % (str(i), str(theta_new))
#print "Diff: %s" % str(meanDiff)
theta = theta_new
i += 1
Z_test = pol.fit_transform(X[test])
Y_hat_test = np.dot(Z_test, theta)
Y_hat = np.dot(Z, theta)
trainError += tools.findError(Y_hat, Y[train])
testError += tools.findError(Y_hat_test, Y[test])
trainError = trainError/len(kf)
testError = testError/len(kf)
iterative_error = [trainError, testError]
errors. append(iterative_error)
return np.asarray(errors)
def set_pdynome_degree(degree, lis):
lis = [lis]
ploy = PolynomialFeatures(degree)
result = ploy.fit_transform(lis)
result = result.tolist()
result = result[0]
return result
def init_predict(mode):
""" 整理为用于预测的 X
i: features
o: X
"""
import scipy.io as sio
import scipy as sp
from sklearn.preprocessing import PolynomialFeatures
uid_ave = sio.loadmat('predict_cut_uid_ave.mat')['X']
poly = PolynomialFeatures(degree=2)
poly_uid_ave = poly.fit_transform(uid_ave)
combined_list = [sp.sparse.csc_matrix(poly_uid_ave)]
if mode == 'f':
X_words = sio.loadmat('predict_cut_Xf.mat')['X']
elif mode == 'c':
X_words = sio.loadmat('predict_cut_Xc.mat')['X']
else:
X_words = sio.loadmat('predict_cut_Xl.mat')['X']
#transformer = TfidfTransformer()
#X_tfidf = transformer.fit_transform(X_words)
combined_list.append(X_words)
X = sp.sparse.hstack(combined_list)
print(X.shape)
return X
def polyRegressionKFold(inputFiles, deg=2):
print "***************************"
print "Degree: %s" % deg
start_time = time.time()
errors = []
for File in inputFiles:
print "___________________________"
print "Data Set: %s" % File
data = tools.readData(File)
data = data[np.argsort(data[:,0])]
X = data[:, :-1]
Y = data[:, len(data[1,:]) - 1]
kf = KFold(len(data), n_folds = 10, shuffle = True)
TrainError = 0
TestError = 0
for train, test in kf:
pol = PolynomialFeatures(deg)
Z = pol.fit_transform(X[train])
Z_test = pol.fit_transform(X[test])
theta = regress(Z, Y[train])
Y_hat = np.dot(Z, theta)
Y_hat_test = np.dot(Z_test, theta)
TrainError += mean_squared_error(Y[train], Y_hat)
TestError += mean_squared_error(Y[test], Y_hat_test)
TestError /= len(kf)
TrainError /= len(kf)
errors.append([TestError, deg])
print "---------------------------"
print "Test Error: %s" % TestError
print "Train Error: %s" % TrainError
time_taken = start_time - time.time()
print "Time Taken for primal: %s" % str(time_taken)
return np.asarray(errors)
def predict(self, X, coefs):
# first column of Z is time
# we will replace the other columns with regressed data
# clean-up from before
Z = self.X.copy()
print type(Z), Z.head()
print type(coefs), coefs.head()
poly = PolynomialFeatures(degree=self.n)
for trial_index, (coefficients, x) in enumerate(izip(coefs, Z)):
print trial_index, coefficients.shape, x.shape
# reshape required by t
t = poly.fit_transform((x[:,0]).reshape(-1,1))
# only regress on data past reference time
t = t[self.reference_time:]
z = np.zeros(x.shape)
# first column is time
z[:,0] = x[:,0]
# columns up to reference time are just 0 and were not regressed
z[:self.reference_time, 1:] = 0
# columns after reference_time were regressed with coefficients
print t.shape, z.shape, coefficients.shape
z[self.reference_time:, 1:] = np.dot(t, coefficients)
Z.iloc[trial_index] = z
return Z
def hidden_layer(self, X, w):
# The dimension of matrix Z is (R + 1) * m. The extra dimension is constant
# extra 1 dimension for bias.
Z = sigmoid(np.dot(X, w.T))
p = PolynomialFeatures(degree = 1)
Z = p.fit_transform(Z)
return Z
def main():
# linear model (using polynomial features)
model = linear_model.Ridge(alpha=0.1)
# get data
out = getData()
X = out["x_train"]
y = out["y_train"]
perc = int(0.75 * len(X))
X_train = X[0:perc]
X_cv = X[perc:]
y_train = y[0:perc]
y_cv = y[perc:]
X_test = out["x_test"]
Id = out["test_id"]
# add bias unit
poly = PolynomialFeatures(degree=3)
X_train = poly.fit_transform(X_train)
# train model
model.fit(X_train, y_train)
# score
X_cv = poly.fit_transform(X_cv)
print model.score(X_cv, y_cv)
# predict
X_test = poly.fit_transform(X_test)
pred = model.predict(X_test)
f = open("submissions/PolyReg3.csv", "w")
f.write("Id,Hazard\n")
for i in xrange(len(pred)):
f.write(str(Id[i]) + "," + str(pred[i]) + "\n")
def logistic_regression(x,y):
"""
Ierative multifeatures regression.
Find the best theta by changing it in each iteration
Print the training and testing errors for each mapping
"""
errors_training_fmeasure = []
errors_training_accuracy = []
errors_testing_fmeasure = []
errors_testing_accuracy = []
regr = LogisticRegressionKClasses()
poly = PolynomialFeatures(degree=1)
# Cross validation
cv = KFold(len(x), n_folds=10)
for train_idx, test_idx in cv:
x_train = x[train_idx]
x_test = x[test_idx]
y_train = y[train_idx]
y_test = y[test_idx]
x_ = poly.fit_transform(x_train)
x_2 = poly.fit_transform(x_test)
regr.fit(x_,y_train)
# Predict over the testing data and getting the error
predicted_y = regr.predict(x_2)
conf_matrix = confusion_matrix(y_test, predicted_y)
precision, recall, f_measure, accuracy = get_measures(conf_matrix, len(set(y_train)))
print 'Precision:', precision, ' Recall:', recall, ' Accuracy:', accuracy, ' F-Measure:', f_measure
def mvr(data):
x = data[:, 0:len(data[0])-1]
y = data[:, -1]
minTestingError = np.inf
for dim in xrange(1,3):
if(dim > 1):
print("Mapping into higher dimension of {} \n".format(dim))
else:
evaluateGradientDesc(data)
print("Explicit solution\n")
poly = PolynomialFeatures(dim)
z = poly.fit_transform(x)
theta = fitModel(z , y)
print("Intercept : {} \nCoefficients : {}\n".format(theta[0], theta[1:]))
testingError, sol = evaluateModel(z,y, False)
if(dim == 1):
print "Testing Error :", testingError
if (testingError < minTestingError):
minTestingError = testingError
optimalDimension = dim
optSol = sol
print "Optimal Dimension : {}, Testing Error : {} ".format(optimalDimension, minTestingError)
return optSol
def prepare(file, survived_info=True):
df = pd.read_csv(file, header=0)
df = pd.concat([df, pd.get_dummies(df['Embarked'], prefix='Embarked')], axis=1)
df = pd.concat([df, pd.get_dummies(df['Sex'], prefix='Sex')], axis=1)
df = pd.concat([df, pd.get_dummies(df['Pclass'], prefix='Pclass')], axis=1)
df = df.fillna(value={'Age': df['Age'].dropna().median(), 'Fare': df['Fare'].dropna().median()})
survived = None
if survived_info:
survived = df['Survived'].values
df = df.drop(['Survived'], axis=1)
ids = df['PassengerId'].values
df = df.drop(['PassengerId', 'Pclass', 'Name', 'Sex', 'Ticket', 'Cabin', 'Embarked'], axis=1)
poly = PolynomialFeatures(interaction_only=True)
polydata = poly.fit_transform(df)
cols = np.hstack((['1s'], df.columns, [None]*(polydata.shape[1] - len(df.columns) -1)))
polydf = pd.DataFrame.from_records(polydata, columns=cols)
if survived_info: polydf['Survived'] = survived
return (polydf, ids)
def batterLife_chargeMoreThan4(chargeTime):
import numpy as np
trainDataArr = np.genfromtxt("trainingdata_batteryLife.txt", delimiter = ",")
trainDataArr = trainDataArr[trainDataArr[ :,0] > 4]
trainData = trainDataArr[:, 0]
trainData = trainData.reshape(-1,1)
trainValue = trainDataArr[:,1]
testData = np.array(chargeTime)
testData = testData.reshape(-1,1)
from sklearn.preprocessing import PolynomialFeatures
from sklearn import linear_model
# Plot outputs
import matplotlib.pyplot as plt
plt.scatter(trainData, trainValue, color='black')
plt.xticks(())
plt.yticks(())
plt.show()
# Fit regression model
poly = PolynomialFeatures(degree = 1)
trainData_ = poly.fit_transform(trainData)
testData_ = poly.fit_transform(testData)
clf = linear_model.LinearRegression()
clf.fit(trainData_, trainValue)
return clf.predict(testData_)
def linearRegreSin(url,degree):
[a,b] = getData(url)
trainA = a[0:139]
trainB = b[0:139]
testA = a[140:]
testB = b[140:]
poly = PolynomialFeatures(degree)
trainA = np.float64(poly.fit_transform(trainA))
testA = np.float64(poly.fit_transform(testA))
theta = np.dot(np.dot(np.linalg.inv(np.dot(trainA.T,trainA)),trainA.T),trainB)
plt.figure(1)
plt.xlabel('x')
plt.ylabel('y')
plt.title('data')
plt.plot(trainA[:,1],trainB,"r*")
y=np.dot(trainA, theta)
print(pow(sum((y-trainB)**2),1/2)/140) #print MSE
y=np.dot(testA, theta)
#plt.plot(testA[:,1], testB, "r.")
plt.plot(testA[:,1],y,"k*")
print(pow(sum((y-testB)**2),1/2)/60) #print MSE
plt.show()
print(theta)
def __init__(self):
self.theta = T.matrix()
# define output for b
combinations = PolynomialFeatures._combinations(2, 3, False, False)
n_output_features_ = sum(1 for _ in combinations) + 1
self.A_b = theano.shared(
value=np.ones((n_output_features_,), dtype=theano.config.floatX),
borrow=True, name='A_b')
self.b_b = theano.shared(value=1.,
borrow=True, name='b_b')
combinations = PolynomialFeatures._combinations(2, 3, False, False)
L = [(self.theta[:, 0] ** 0).reshape([-1, 1])]
for i, c in enumerate(combinations):
L.append(self.theta[:, c].prod(1).reshape([-1, 1]))
self.XF3 = T.concatenate(L, axis=1)
b = (T.dot(self.XF3, self.A_b) + self.b_b).reshape([-1, 1])
# define output for k
combinations = PolynomialFeatures._combinations(2, 2, False, False)
n_output_features_ = sum(1 for _ in combinations) + 1
self.rho_k = theano.shared(
value=np.ones((n_output_features_,), dtype=theano.config.floatX),
borrow=True, name='rho_k')
combinations = PolynomialFeatures._combinations(2, 2, False, False)
L = [(self.theta[:, 0] ** 0).reshape([-1, 1])]
for i, c in enumerate(combinations):
L.append(self.theta[:, c].prod(1).reshape([-1, 1]))
self.XF2 = T.concatenate(L, axis=1)
k = T.dot(self.XF2, self.rho_k).reshape([-1, 1])
self.outputs = [T.concatenate([b, k], axis=1)]
self.inputs = [self.theta]
self.trainable_weights = [self.A_b, self.b_b, self.rho_k]
def myTradingSystem(DATE, OPEN, HIGH, LOW, CLOSE, VOL, OI, P, R, RINFO, exposure, equity, settings):
""" This system uses linear regression to allocate capital into the desired equities"""
# Get parameters from setting
nMarkets = len(settings['markets'])
lookback = settings['lookback']
dimension = settings['dimension']
threshold = settings['threshold']
pos = np.zeros(nMarkets, dtype=np.float)
poly = PolynomialFeatures(degree=dimension)
for market in range(nMarkets):
reg = linear_model.LinearRegression()
try:
reg.fit(poly.fit_transform(np.arange(lookback).reshape(-1, 1)), CLOSE[:, market])
trend = (reg.predict(poly.fit_transform(np.array([[lookback]]))) - CLOSE[-1, market]) / CLOSE[-1, market]
if abs(trend[0]) < threshold:
trend[0] = 0
pos[market] = np.sign(trend)
# for NaN data set position to 0
except ValueError:
pos[market] = .0
return pos, settings
def prob_max(x):
poly=PolynomialFeatures(degree=2)
x=poly.fit_transform(x)
####define best fit coefficient arrays
theta_0=np.array([5.017034759466216798e+00,-4.953976374628412532e-02,-5.853604893727188709e-03,-1.732076056200582692e-01,4.646876717720006822e-02,-2.787195959859810248e-04,-1.222728739255723981e-07,6.120106921025333935e-02,4.604924515407455714e-06,-1.475861223279032741e-01,-4.060326310707941784e-09,1.177855732870812001e-02,3.113699082333943463e-02,-8.110887996756119586e-12,-1.113811480228766704e-05,-1.501651909640449069e-07,-2.190797370951344465e-06,-1.718990505473245339e-05,-1.199898098055512375e-13,-2.571924773608319866e-07,-2.147269697093823931e-12,-3.256296536440236682e-05,-2.581007347409745425e-05,1.392377894191479523e-03,-4.129157456238496948e-02,-1.811677361205055875e-02,-7.083807139833804416e-06,4.116671309652412958e-02,3.361594896247442773e-04,-8.223201336497298203e-03,-1.862209709284966395e-07,1.527880447451521184e-02,-3.672245027121902317e-02,-4.975817315933817863e-10,-6.237344094335352815e-04,-1.217106713769066128e-05,-1.489610233924158246e-04,-1.156461881655085214e-03,-5.159561821638818347e-12,-1.884192981459143558e-05,-1.825179242529750414e-10,-5.438522396156177874e-07,4.167833399722946711e-05,5.607144654864255374e-03,-3.093787958451529527e-02,-2.041422430639949412e-04,7.895983583095988675e-03,1.293062803926413491e-02,5.899640081165494730e-03,-1.021176015149306061e-05,8.486220614842233598e-03,5.822368958314040610e-03,-2.243937133831174112e-08,-8.464968966797879399e-03,-1.906386791427585779e-04,-1.795243901952780228e-03,-1.046895210502369993e-02,-3.330917120202175767e-10,-4.235251180738666644e-04,-5.694559236692822056e-09,-1.583929993116185621e-03,1.629024063907276165e-01,-6.967989967191325247e-03,-3.673107962032413740e-06,-2.280088579624509337e-01,1.726846693277796316e-04,1.013912471248917396e-01,-7.647706080406362405e-08,-3.240179256710575273e-01,1.214811767523774205e-01,-3.401281050759457049e-10,-1.670938331047893612e-07,-7.369899627351106136e-06,-9.856333774434332797e-05,-4.534506039623955074e-05,-9.599184784444142215e-12,-5.151527253102048208e-06,-1.030689454605035745e-10,4.646876717720006822e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-2.787195959859810248e-04,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-1.222728739255723981e-07,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,6.120106921025333935e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,4.604924515407455714e-06,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-1.475861223279032741e-01,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-4.060326310707941784e-09,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,1.177855732870812001e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,3.113699082333943463e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-8.110887996756119586e-12,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-1.113811480228766704e-05,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-1.501651909640449069e-07,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-2.190797370951344465e-06,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-1.718990505473245339e-05,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-1.199898098055512375e-13,0.000000000000000000e+00,0.000000000000000000e+00,-2.571924773608319866e-07,0.000000000000000000e+00,-2.147269697093823931e-12])
theta_1=np.array([-9.861773710361221745e+00,1.930173314618176539e-01,6.178220889126870112e-03,9.590504030349773779e-02,-2.071552578564340164e-01,1.061401114719375260e-01,3.276754675639340086e-02,-1.761411784826558136e-02,-1.219468120911304441e-06,-9.174348236081142360e-02,2.132582599900693932e-02,-1.168137887722866912e-02,1.014151234082172059e-01,9.598987135568204463e-04,-4.542651588690940767e-02,-7.514592183950008714e-04,1.113651743862166532e-03,3.535033504077587929e-02,1.348878960300472899e-06,4.158088521609443200e-02,1.744377835470558925e-06,-8.830070079582454969e-04,-6.118986593694282407e-05,-4.784785490618059583e-04,6.231388236713353984e-02,1.984193321394733464e-02,3.807758267577563555e-02,-1.857758661936751918e-02,-8.902117282652563328e-05,1.684544497032977118e-03,-4.354918224284388961e-02,8.135671785350261087e-03,1.838040795364327554e-03,4.648089395429296639e-02,1.603282923510754299e-02,-5.706248765095311287e-02,6.474737189221846378e-02,-1.666585875194382532e-02,5.800179529291954185e-05,6.960244357250958136e-02,1.482721160150063508e-04,-5.299760763074679222e-07,-4.512899253144341872e-05,-9.330422825892547602e-04,-3.692049341246863322e-04,-7.641113350637301687e-04,-3.553288559473667197e-04,-3.424266483519060756e-03,4.323086081437536800e-04,-4.955185382381825611e-04,-5.468633412309427573e-03,3.023053081335558886e-04,2.032432933463332054e-03,-1.868881428527514009e-04,5.907286677952040300e-03,1.224575926635180362e-03,1.491552037995557810e-03,3.744487993794240379e-03,-1.585824627682363985e-03,4.626090019667926378e-03,2.914276434916693195e-04,-6.421237001048539506e-04,1.343912634023189216e-02,1.202887078507273999e-02,4.579648647433440592e-03,-4.573005453417482836e-05,-2.603037492365091118e-02,1.093608117200833424e-01,3.532167048002045617e-01,-1.790610728587208392e-02,-7.755213616683120925e-02,-5.213887650785711293e-03,-1.747560651202587356e-01,-4.635745132339050972e-02,-5.689835106400319142e-02,1.079103168240419384e-04,8.490464847112829186e-03,8.373013610258914587e-05,-2.071552578564340164e-01,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,1.061401114719375260e-01,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,3.276754675639340086e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-1.761411784826558136e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-1.219468120911304441e-06,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-9.174348236081142360e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,2.132582599900693932e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-1.168137887722866912e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,1.014151234082172059e-01,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,9.598987135568204463e-04,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-4.542651588690940767e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-7.514592183950008714e-04,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,1.113651743862166532e-03,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,3.535033504077587929e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,1.348878960300472899e-06,0.000000000000000000e+00,0.000000000000000000e+00,4.158088521609443200e-02,0.000000000000000000e+00,1.744377835470558925e-06])
theta_2=np.array([-2.604982997969506187e+01,2.522175474048852784e-01,6.275718741926675920e-03,1.273176496282046599e-01,-1.716361908427019300e-01,-8.312891928874267811e-02,4.068642760504040390e-02,-2.445951924349220458e-02,-8.746331909292573688e-07,-1.542657353435612777e-02,-1.765684782956331370e-02,-3.195224775777173168e-04,2.484350665759416446e-02,4.813993958703906978e-03,1.759866699719525307e-01,5.747258345660388864e-04,-1.022129045161229450e-03,5.567310929387970370e-02,-9.063835339582872293e-07,-8.930479773136143495e-02,-9.138473645722535673e-07,-7.459379939882724523e-04,-4.125238423403655301e-05,-4.278814974555324602e-04,1.234252674940865789e-02,4.708747007997553247e-02,2.657070242802176546e-02,6.926664427951148562e-02,-6.384822293781164664e-05,4.964280033292678418e-02,9.853135356553717472e-02,-2.621681271491586862e-02,6.630289966406467672e-02,-2.208061355155441774e-01,4.922574438806641417e-02,4.310173077725486246e-02,-5.622794820973487512e-02,1.006576646572381883e-01,-3.897449196020566275e-05,-7.080593340274707326e-03,-7.767702598866720021e-05,-3.990070230109308789e-07,-1.651061082255117919e-05,1.537024690049966936e-03,8.005698436542285070e-04,8.994568249232704014e-04,5.470196351385650481e-04,-2.455970000128474082e-03,4.988277998095904915e-04,1.262763556509414152e-03,4.601679612131920685e-03,-1.194497842888761268e-04,2.882224654372331132e-03,5.875401491502118233e-04,-2.458015081252763658e-03,5.859965255224170106e-04,-2.547687917446368093e-04,-2.516120690268733393e-03,2.300462784971263851e-03,-2.423523210845587861e-03,-1.539288004294190964e-04,-1.260645266526524456e-02,-2.136594669075533859e-02,-1.240381092246360673e-02,1.775253607050698845e-02,-3.279874465984122252e-05,1.667948986384345557e-03,-1.177656364439296638e-01,-8.947706286380961412e-04,5.282554584883104691e-03,9.528953029071411673e-02,-1.953324553475337816e-03,1.692159896831275101e-01,6.332910268512657870e-02,-3.059270306265245501e-02,-7.251068271668771679e-05,-2.748819360572268139e-02,-4.386467349947201168e-05,-1.716361908427019300e-01,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-8.312891928874267811e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,4.068642760504040390e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-2.445951924349220458e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-8.746331909292573688e-07,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-1.542657353435612777e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-1.765684782956331370e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-3.195224775777173168e-04,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,2.484350665759416446e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,4.813993958703906978e-03,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,1.759866699719525307e-01,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,5.747258345660388864e-04,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-1.022129045161229450e-03,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,5.567310929387970370e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-9.063835339582872293e-07,0.000000000000000000e+00,0.000000000000000000e+00,-8.930479773136143495e-02,0.000000000000000000e+00,-9.138473645722535673e-07])
theta_3=np.array([-2.972725322795918140e-02,-2.504227156229747453e-01,-9.722118342779062158e-03,1.229149113213241912e-01,2.039923850853684467e-02,-1.805107341267933943e-02,7.334563069172345476e-03,-6.475321568310828764e-04,-8.474944289249388250e-08,9.714545617984883855e-05,-2.075035998257516458e-07,-1.221820060933139164e-05,-1.714475447964966190e-02,-2.129377838506303893e-03,-1.277321374533818017e-06,-2.380156363764723250e-06,-5.273025783548628525e-06,-1.984111789391731009e-03,-1.335426121119178434e-07,3.339996589013074558e-04,-2.141039464532945376e-07,2.576647414932395786e-03,2.945797215512836505e-06,-1.895000552612198606e-04,-1.462288947682845522e-02,-1.951654268095479733e-02,-1.630737487857820273e-02,-5.655678104343885015e-02,-6.186709331152055607e-06,-2.000570956968860184e-02,-1.460798045208372536e-05,-9.892777618470509349e-04,-6.134943418829629652e-02,5.204243735868804843e-02,-6.976997540713989398e-05,-1.924795146172466416e-04,-3.585644621246710678e-04,-8.751744876445026466e-02,-5.742332320812468485e-06,-2.493414480788682872e-02,-1.819883544853002577e-05,1.673188626427698019e-06,-2.199004526442708865e-05,3.929065891591175703e-03,3.411106034336343351e-03,4.689455918427083009e-03,-1.623583183295337906e-02,-2.379764356421232188e-04,4.563617516957610247e-03,-5.845377676580722996e-04,-5.550332977089329420e-03,5.817926665026248653e-03,3.489254807540806587e-03,-8.968364091790517831e-04,-2.770023159211470760e-03,-4.227833625220314175e-03,1.685174688793472349e-03,-3.707142912226834078e-04,-5.865829701672146956e-03,-5.678036659941369801e-04,8.344188249964974876e-05,-2.863247383273172242e-02,-6.482258485425367728e-03,-4.199374526758931081e-02,-1.256077522453134809e-02,-3.178104108468527999e-06,-3.440396173308768457e-02,-9.901849306080791411e-06,-3.180423753092536477e-05,-7.452030759889874401e-02,-6.907406950607837548e-02,5.971308793973397274e-07,-1.155260382492086013e-04,-2.332571299853613211e-04,1.410515664042338024e-01,-1.068340896895342663e-05,2.499449671921087357e-01,-1.027698942975813230e-05,2.039923850853684467e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-1.805107341267933943e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,7.334563069172345476e-03,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-6.475321568310828764e-04,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-8.474944289249388250e-08,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,9.714545617984883855e-05,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-2.075035998257516458e-07,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-1.221820060933139164e-05,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-1.714475447964966190e-02,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-2.129377838506303893e-03,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-1.277321374533818017e-06,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-2.380156363764723250e-06,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-5.273025783548628525e-06,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-1.984111789391731009e-03,0.000000000000000000e+00,0.000000000000000000e+00,0.000000000000000000e+00,-1.335426121119178434e-07,0.000000000000000000e+00,0.000000000000000000e+00,3.339996589013074558e-04,0.000000000000000000e+00,-2.141039464532945376e-07,])
#####calculate probabilities
z_0=np.sum(x*theta_0)
z_1=np.sum(x*theta_1)
z_2=np.sum(x*theta_2)
z_3=np.sum(x*theta_3)
p_0=1./(1.+np.exp(-z_0))
p_1=1./(1.+np.exp(-z_1))
p_2=1./(1.+np.exp(-z_2))
p_3=1./(1.+np.exp(-z_3))
prob_arra=np.array([p_0, p_1, p_2, p_3])
return prob_arra.argmax()
def poly_model(ins,outs,degrees):
poly = PolynomialFeatures(degree=degrees)
X = poly.fit_transform(ins)
regr = linear_model.LinearRegression()
regr.fit(X, outs)
print_model("poly-"+str(degrees), regr, X, outs)
def evaluateGradientDesc(data): #Function to evaluate Gradient Descent Algorithm in terms of testing Error
poly = PolynomialFeatures(1)
x = data[:, 0:len(data[0])-1]
y = data[:, -1]
z = poly.fit_transform(x)
testingError, sol = evaluateModel(z,y, True)
print "Iterative solution\nTesting error : ", testingError , "\n"
from scipy.stats import boxcox
X_train_transformed = X_train.copy()
X_train_transformed['Fare'] = boxcox(X_train_transformed['Fare'] + 1)[0]
X_test_transformed = X_test.copy()
X_test_transformed['Fare'] = boxcox(X_test_transformed['Fare'] + 1)[0]
# Rescale data
from sklearn.preprocessing import MinMaxScaler
scaler = MinMaxScaler()
X_train_transformed_scaled = scaler.fit_transform(X_train_transformed)
X_test_transformed_scaled = scaler.transform(X_test_transformed)
# Get polynomial features
from sklearn.preprocessing import PolynomialFeatures
poly = PolynomialFeatures(degree=2).fit(X_train_transformed)
X_train_poly = poly.transform(X_train_transformed_scaled)
X_test_poly = poly.transform(X_test_transformed_scaled)
# Debug
print(poly.get_feature_names())
# Select features using chi-squared test
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
## Get score using original model
logreg = LogisticRegression(C=1)
logreg.fit(X_train, y_train)
scores = cross_val_score(logreg, X_train, y_train, cv=10)
print('CV accuracy (original): %.3f +/- %.3f' % (np.mean(scores), np.std(scores)))
highest_score = np.mean(scores)
v.feature_names_
#결측치 처리
from sklearn.preprocessing import Imputer
imp = Imputer(missing_values='NaN', strategy='mean', axis=0)
imp.fit_transform([[1, 2], [np.nan, 3], [7, 6]])
#파생변수 생성
# [1, a, b, a^2, ab, b^2]
from sklearn.preprocessing import PolynomialFeatures
X = np.arange(6).reshape(3, 2)
X
poly = PolynomialFeatures(2)
poly.fit_transform(X)
## [1, a, b, a^2, ab, b^2]
#apply와 같은 효과
from sklearn.preprocessing import FunctionTransformer
def all_but_first_column(X):
return X[:, 1:]
X = np.arange(12).reshape(4, 3)
X
FunctionTransformer(all_but_first_column).fit_transform(X)
def Lasso_Regression(degree, alpha):
return Pipeline([
("poly", PolynomialFeatures(degree=degree)), # 建立多项式
("std_scaler", StandardScaler()), # 归一化处理
("ridge_reg", Lasso(alpha=alpha)) # 岭回归方程
])
# Feature Scaling
"""from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)
sc_y = StandardScaler()
y_train = sc_y.fit_transform(y_train)"""
#Linear Regression
from sklearn.linear_model import LinearRegression
lin_reg = LinearRegression()
lin_reg.fit(X,y)
#Polynomial Linear Regression
from sklearn.preprocessing import PolynomialFeatures
poly_reg = PolynomialFeatures(degree=4)
X_poly = poly_reg.fit_transform(X)
lin_reg_2 = LinearRegression()
lin_reg_2.fit(X_poly, y)
# Visualising the Linear Regression results
plt.scatter(X, y, color = 'red')
plt.plot(X, lin_reg.predict(X), color = 'blue')
plt.title('Truth or Bluff (Linear Regression)')
plt.xlabel('Position level')
plt.ylabel('Salary')
plt.show()
# Visualising the Polynomial Regression results
plt.scatter(X, y, color = 'red')
-1.17165272, -0.89129801, -0.85572252, -0.7736467, -0.21234812,-0.12717219])
x_test = np.array([0.31273956 , 0.46122891, 0.4917774, 0.7039386, 0.84386983, 0.97020886])
y_test = np.array([0.909136, 0.38747724, -0.92084687, -1-0.03804487,.03453301,-0.1177253])
# create matrix versions of these arrays
X_train = x_train[:, np.newaxis]
X_test = x_test[:, np.newaxis]
colors = ['teal', 'yellow' ,'green', 'gold']
lw = 2
train_error = []
test_error = []
for degree in range(11):
for count, degree in enumerate([degree]):
fig.clf()
model = make_pipeline(PolynomialFeatures(degree), Ridge(alpha = 0))
model.fit(X_train, y_train)
train_error.append(mean_squared_error(y_train, model.predict(X_train)))
test_error.append(mean_squared_error(y_test, model.predict(X_test)))
plt.plot(np.arange(11), train_error, color='green', label='train')
plt.plot(np.arange(11), test_error, color='red', label='test')
plt.ylim((0.0, 1e0))
plt.ylabel('Mean Squared Error)')
plt.xlabel('Degree')
plt.legend(loc='lower left')
fig.savefig('Testing_Answer4_1.png', bbox_inches='tight')
y = y[:-forecast_out]
print('Dimension of X', X.shape)
print('Dimension of X_lately', X_lately.shape)
print('Dimension of y', y.shape)
# Separation of training and testing of model by cross validation train test split
X_train, X_test, y_train, y_test = model_selection.train_test_split(
X, y, test_size=0.2)
# Linear regression
clfreg = LinearRegression(n_jobs=-1)
clfreg.fit(X_train, y_train)
# Quadratic Regression 2
clfpoly2 = make_pipeline(PolynomialFeatures(2), Ridge())
clfpoly2.fit(X_train, y_train)
# Quadratic Regression 3
clfpoly3 = make_pipeline(PolynomialFeatures(3), Ridge())
clfpoly3.fit(X_train, y_train)
# KNN Regression
clfknn = KNeighborsRegressor(n_neighbors=2)
clfknn.fit(X_train, y_train)
confidencereg = clfreg.score(X_test, y_test)
confidencepoly2 = clfpoly2.score(X_test, y_test)
confidencepoly3 = clfpoly3.score(X_test, y_test)
confidenceknn = clfknn.score(X_test, y_test)
def predictStockPrices(df):
dfreg = df.loc[:, ['Adj Close', 'Volume']]
dfreg['HL_PCT'] = (df['High'] - df['Low']) / df['Close'] * 100.0
dfreg['PCT_change'] = (df['Close'] - df['Open']) / df['Open'] * 100.0
print(dfreg.tail())
# cleanup process
# --------------------------------------------------------------------
# drop missing values
dfreg.fillna(value=-99999, inplace=True)
# we want to separate 1 percent of the data to forecast
forecast_out = int(math.ceil(0.01 * len(dfreg)))
# we want to predict the AdjClose
forecast_col = 'Adj Close'
dfreg['label'] = dfreg[forecast_col].shift(-forecast_out)
X = np.array(dfreg.drop(['label'], 1))
# scale the X so that everyone can have the same distribution for linear regression
X = sk.preprocessing.scale(X)
# find data series of late X and early X (train) for model generation and evaluation
X_lately = X[-forecast_out:]
X = X[:-forecast_out]
# Separate label and identify it as y
y = np.array(dfreg['label'])
y = y[:-forecast_out]
print('Dimension of X', X.shape)
print('Dimension of y', y.shape)
# Separation of training and testing of model by cross validation train test split
X_train, X_test, y_train, y_test = sk.model_selection.train_test_split(
X, y, test_size=0.2)
# Linear Regression
clfreg = LinearRegression(n_jobs=-1)
clfreg.fit(X_train, y_train)
# Lasso Regression
clflasso = Lasso(selection='random')
clflasso.fit(X_train, y_train)
# Quadratic Regression 2
clfpoly2 = make_pipeline(PolynomialFeatures(2), Ridge())
clfpoly2.fit(X_train, y_train)
# Quadratic Regression 3
clfpoly3 = make_pipeline(PolynomialFeatures(3), Ridge())
clfpoly3.fit(X_train, y_train)
# KNN
clfknn = KNeighborsRegressor(n_neighbors=2)
clfknn.fit(X_train, y_train)
# Test the models
confidencereg = clfreg.score(X_test, y_test)
confidencepoly2 = clfpoly2.score(X_test, y_test)
confidencepoly3 = clfpoly3.score(X_test, y_test)
confidenceknn = clfknn.score(X_test, y_test)
confidencelasso = clflasso.score(X_test, y_test)
print("The linear regression confidence is ", confidencereg)
print("The quadratic regression 2 confidence is ", confidencepoly2)
print("The quadratic regression 3 confidence is ", confidencepoly3)
print("The knn regression confidence is ", confidenceknn)
print("The knn lasso confidence is ", confidencelasso)
# Predict
predictAndPlot(clfreg, X_lately, dfreg.copy(), confidencereg, forecast_out)
predictAndPlot(clfpoly2, X_lately, dfreg.copy(), confidencepoly2,
forecast_out)
predictAndPlot(clfpoly3, X_lately, dfreg.copy(), confidencepoly3,
forecast_out)
predictAndPlot(clfknn, X_lately, dfreg.copy(), confidenceknn, forecast_out)
predictAndPlot(clflasso, X_lately, dfreg.copy(), confidencelasso,
forecast_out)
#1. kutuphaneler
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import PolynomialFeatures
import matplotlib.pyplot as plt
# veri yukleme
df = pd.read_csv('winequality-red.csv')
X = df[['quality']]
y = df[['fixed acidity', 'volatile acidity', 'citric acid', 'residual sugar', 'chlorides', 'free sulfur dioxide', 'total sulfur dioxide', 'density', 'pH', 'sulphates', 'alcohol']]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
model = PolynomialFeatures(degree=4)
y_ = model.fit_transform(y)
y_test_ = model.fit_transform(y_test)
print(y_, y_test_)
lg = LinearRegression()
lg.fit(y_,X)
predicted_data = lg.predict(y_test_)
predicted_data = np.round(predicted_data)
print(mean_squared_error(X_test,predicted_data))
print(predicted_data)
import matplotlib.pyplot as plt
import pandas as pd
# Importing the dataset
dataset = pd.read_csv('Position_Salaries.csv')
X = dataset.iloc[:, 1:2].values
y = dataset.iloc[:, 2].values
# Fitting Linear Regression to the dataset
from sklearn.linear_model import LinearRegression
lin_reg = LinearRegression()
lin_reg.fit(X, y)
# Fitting Polynomial Regression to the dataset
from sklearn.preprocessing import PolynomialFeatures
poly_reg = PolynomialFeatures(degree=10)
X_poly = poly_reg.fit_transform(X)
lin_reg_2 = LinearRegression()
lin_reg_2.fit(X_poly, y)
# Visualising the Linear Regression Results
plt.scatter(X, y, color='red')
plt.plot(X, lin_reg.predict(X), color='blue')
plt.title('Truth or Bluff (Linear Regression)')
plt.xlabel('Position Level')
plt.ylabel('Salary')
plt.show()
# Visualising the Polynomial Regression Results
X_grid = np.arange(min(X), max(X), 0.1)
# Employ a quadratic regression to smooth win share vs age data import operator import numpy as np import matplotlib.pyplot as plt from sklearn.linear_model import LinearRegression from sklearn.metrics import mean_squared_error, r2_score from sklearn.preprocessing import PolynomialFeatures x = wsby['Age'].values.reshape(-1, 1) y = wsby['WS'] polynomial_features= PolynomialFeatures(degree=2) x_poly = polynomial_features.fit_transform(x) model = LinearRegression() model.fit(x_poly, y) y_poly_pred = model.predict(x_poly) rmse = np.sqrt(mean_squared_error(y,y_poly_pred)) r2 = r2_score(y,y_poly_pred) # R-squared is 0.8705593525409101, pretty good plt.scatter(x, y, s=10) # sort the values of x before line plot sort_axis = operator.itemgetter(0) sorted_zip = sorted(zip(x,y_poly_pred), key=sort_axis) x, y_poly_pred = zip(*sorted_zip)
def _get_polynomials(self, x):
poly = PolynomialFeatures(degree=self.degree)
x_poly = poly.fit_transform(x.reshape(-1, 1))
return x_poly
def Polynomial_Regression(degree):
return Pipeline([
("poly", PolynomialFeatures(degree=degree)), # 建立多项式
("std_scaler", StandardScaler()), # 归一化处理
("lin_reg", LinearRegression()) # 回归方程
])
normalizer = preprocessing.Normalizer().fit(X)
print(normalizer.transform(X))
# Binarization
# Feature binarization
print("Feature binarization")
X = [[1., -1., 2.], [2., 0., 0.], [0., 1., -1.]]
binarizer = preprocessing.Binarizer().fit(X)
print(binarizer.transform(X))
# Imputation of missing values
print("Imputation of missing values")
from sklearn.preprocessing import Imputer
imp = Imputer(missing_values='NaN', strategy='mean', verbose=0)
imp.fit([[1, 2], [np.nan, 3], [7, 6]])
X = [[np.nan, 2], [6, np.nan], [7, 6]]
print(imp.transform(X))
# Generating polynomial features
print("Generating polynomial features")
from sklearn.preprocessing import PolynomialFeatures
X = np.arange(6).reshape(3, 2)
poly = PolynomialFeatures(2)
print(poly.fit_transform(X))
X = np.arange(9).reshape(3, 3)
poly = PolynomialFeatures(degree=3, interaction_only=True)
print(poly.fit_transform(X))
lines = fr.readlines()
for line in lines: # 逐行进行操作，循环遍历所有数据
items = line.strip().split(',')
datasets_X.append(int(items[0])) #将读取的数据转换为int型，并分别写入datasets_X和datasets_Y
datasets_Y.append(int(items[1]))
length = len(datasets_X)
datasets_X = np.array(datasets_X).reshape([length, 1])
datasets_Y = np.array(datasets_Y)
minX = min(datasets_X)
maxX = max(datasets_X)
X = np.arange(minX, maxX).reshape([-1, 1])
# degree=2 表示建立datasets_X的二次多项式特征X_poly
poly_reg = PolynomialFeatures(degree=2)
X_poly = poly_reg.fit_transform(datasets_X)
lin_reg_2 = linear_model.LinearRegression()
lin_reg_2.fit(X_poly, datasets_Y)
print(poly_reg)
#查看回归方程系数
print('Cofficients:', lin_reg_2.coef_)
#查看回归方程截距
print('intercept', lin_reg_2.intercept_)
# 图像中显示
plt.scatter(datasets_X, datasets_Y, color='red')
plt.plot(X, lin_reg_2.predict(poly_reg.fit_transform(X)), color='blue')
plt.xlabel('Area')
plt.ylabel('Price')
def train_model_lassoLARS_style(predictors, predictants, alpha, deg):
Vandermonde = PolynomialFeatures(degree=deg)
Vandermonde = Vandermonde.fit_transform(predictors)
LinModel = linear_model.LassoLars(alpha=alpha)
LinModel = LinModel.fit(Vandermonde, predictants)
return LinModel
# reading in the data file
A = np.loadtxt("steel_composition_train_2.csv", delimiter=",", skiprows=1)
numOfRows = A.shape[0]
numOfCols = A.shape[1]
# deleting the first and last column
trainingData = np.delete(A, [0, numOfCols-1], 1)
# saving the last column as target vector
targetVector_train = A[:,-1]
# predict the values from test set
B = np.loadtxt("steel_composition_test.csv", delimiter=",", skiprows=1)
testData = np.delete(B, 0, 1)
X_train, X_test, y_train, y_test = cross_validation.train_test_split(trainingData, targetVector_train, test_size=0.4, random_state=0)
poly = PolynomialFeatures(3)
features_train = poly.fit_transform(X_train)
features_test = poly.fit_transform(X_test)
regr = linear_model.LinearRegression()
#trainFeatures_T = features_train.transpose()
trainFeatures_T = trainingData.transpose()
#phi_T_phi = np.dot(trainFeatures_T, features_train)
phi_T_phi = np.dot(trainFeatures_T, trainingData)
ident = np.eye(phi_T_phi.shape[0], phi_T_phi.shape[1])
#for k in range(-40, 41):
for k in range(18, 19):
lamda = np.exp(k)
lamdaEye = np.dot(lamda, ident)
matrix_1 = np.add(lamdaEye, phi_T_phi)
matrix_1_inv = inv(matrix_1)
import pylab as plt
import pandas as pd
#importing dataset
dataset = pd.read_csv('Position_Salaries.csv')
X = dataset.iloc[:, 1:-1].values
y = dataset.iloc[:, -1].values
#fitting linear regression
from sklearn.linear_model import LinearRegression
lin_regressor = LinearRegression()
lin_regressor.fit(X, y)
#fitting polynomial regression to the dataset
from sklearn.preprocessing import PolynomialFeatures
poly_regressor = PolynomialFeatures(degree=2)
X_poly = poly_regressor.fit_transform(X)
lin_regressor2 = LinearRegression()
lin_regressor2.fit(X_poly, y)
#visualization of linear regression resutls
plt.scatter(X, y, color='red')
plt.plot(X, lin_regressor.predict(X))
plt.title('Linear Regression (Truth)')
plt.xlabel('Positoin Level')
plt.ylabel('Salary')
plt.show()
#visualization of polynomial linear regression
plt.scatter(X, y, color='red')
plt.plot(X, lin_regressor2.predict(poly_regressor.fit_transform(X)))
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns
#Let's examine the distribution of the predicted values of the training data.
Title = 'Distribution Plot of Predicted Value Using Training Data vs Training Data Distribution'
DistributionPlot(y_train, yhat_train, "Actual Values (Train)", "Predicted Values (Train)", Title)
Title='Distribution Plot of Predicted Value Using Test Data vs Data Distribution of Test Data'
DistributionPlot(y_test,yhat_test,"Actual Values (Test)","Predicted Values (Test)",Title)
from sklearn.preprocessing import PolynomialFeatures
#Overfitting
#Let's use 55 percent of the data for testing and the rest for training:
x_train, x_test, y_train, y_test = train_test_split(x_data, y_data, test_size=0.45, random_state=0)
#We will perform a degree 5 polynomial transformation on the feature 'horse power'.
pr = PolynomialFeatures(degree=5)
x_train_pr = pr.fit_transform(x_train[['horsepower']])
x_test_pr = pr.fit_transform(x_test[['horsepower']])
pr
#Now let's create a linear regression model "poly" and train it.
poly = LinearRegression()
poly.fit(x_train_pr, y_train)
#We can see the output of our model using the method "predict." then assign the values to "yhat".
yhat = poly.predict(x_test_pr)
yhat[0:5]
#Let's take the first five predicted values and compare it to the actual targets.
print("Predicted values:", yhat[0:4])
print("True values:", y_test[0:4].values)
PollyPlot(x_train[['horsepower']], x_test[['horsepower']], y_train, y_test, poly,pr)
#R^2 of the training data:
model = SelectFromModel(clf, prefit=True) X_new = model.transform(X) X_new.shape(150, 2) #reg = RandomForestRegressor(n_estimators=500,random_state=0) #reg.fit(X_train,y_train) percent_diff_other = ((y_test - pred) / (y_test)) * 100 from sklearn import datasets from sklearn import metrics from sklearn.ensemble import ExtraTreesClassifier dataset = datasets.load_iris() model = ExtraTreesClassifier() model.fit() from sklearn.metrics import accuracy_score feature_importance = reg.feature_importances_ np_arr = np.array(y_test, dtype=pd.Float64Index) score = accuracy_score(np_arr[0], predictions[0]) accuracy_score(y_test, pred) from sklearn.preprocessing import PolynomialFeatures from sklearn import linear_model poly = PolynomialFeatures(degree=2) X_train_ = poly.fit_transform(X_train) y_train_ = poly.fit_transform(y_train) X_test_ = poly.fit_transform(X_test) #X_train, X_test, y_train, y_test = train_test_split(X_, y_, test_size=0.2,random_state=0) preds = GenerateLinearRegressionModel(X_train, y_train, X_test) from sklearn.model_selection import cross_val_score scores = cross_val_score(estimator=reg, X=X_train, y=y_train, cv=10)
}
return results
def runLR(train_X, train_y, test_X, test_y, test_X2, params):
print('Train LR')
model = RandomForestClassifier(**params)
model.fit(train_X, train_y)
print('Predict 1/2')
pred_test_y = model.predict_proba(test_X)[:, 1]
print('Predict 2/2')
pred_test_y2 = model.predict_proba(test_X2)[:, 1]
return pred_test_y, pred_test_y2
target = train['redemption_status'].values
poly = PolynomialFeatures(degree=2)
sc = StandardScaler()
lr_params = {'n_estimators': 1000}
results = run_cv_model(
sc.fit_transform(poly.fit_transform(train[train_cols].fillna(0).values)),
sc.fit_transform(poly.fit_transform(test[train_cols].fillna(0).values)),
target, runLR, lr_params, auc, 'lr')
day = 2
sub = 3
name = f"day_{day}_sub_{sub}"
tmp = dict(zip(test.id.values, results['test']))
answer1 = pd.DataFrame()
answer1['id'] = test.id.values
answer1['redemption_status'] = answer1['id'].map(tmp)
answer1.to_csv(f'{name}.csv', index=None)
# imputer is for handling missing values
from sklearn.preprocessing import Imputer
imputer = Imputer(strategy='median')
poly_target = poly_features['TARGET']
poly_features = poly_features.drop(columns=['TARGET'])
# Need to impute missing values
poly_features = imputer.fit_transform(poly_features)
poly_features_test = imputer.transform(poly_features_test)
from sklearn.preprocessing import PolynomialFeatures
# Create the polynomial object with specified degree
poly_transformer = PolynomialFeatures(degree=3)
# Train the polynomial features
poly_transformer.fit(poly_features)
# Transform the features
poly_features = poly_transformer.transform(poly_features)
poly_features_test = poly_transformer.transform(poly_features_test)
#print('Polynomial Features shape: ', poly_features.shape)
#print(poly_transformer.get_feature_names(input_features = ['EXT_SOURCE_1', 'EXT_SOURCE_2', 'EXT_SOURCE_3', 'DAYS_BIRTH'])[:34])
poly_features = pd.DataFrame(poly_features,
columns=poly_transformer.get_feature_names([
'EXT_SOURCE_1', 'EXT_SOURCE_2',
'EXT_SOURCE_3', 'DAYS_BIRTH'
]))
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
# Importing the dataset
dataset = pd.read_csv('Position_Salaries.csv')
X = dataset.iloc[:, 1:2].values
y = dataset.iloc[:, 2].values
#Fitting Linear Regression to the Dataset
from sklearn.linear_model import LinearRegression
lin_reg = LinearRegression()
lin_reg.fit(X, y)
#Fitting Polynomial Regressor to the dataset
from sklearn.preprocessing import PolynomialFeatures
poly_reg = PolynomialFeatures(degree=4)
X_poly = poly_reg.fit_transform(X)
poly_reg.fit(X_poly, y)
lin_reg2 = LinearRegression()
lin_reg2.fit(X_poly, y)
#Visualize Linear Regression Result
plt.scatter(X, y, color="red")
plt.plot(X, lin_reg.predict(X), color="green")
plt.title("Linear Regression")
plt.xlabel("Position Level")
plt.ylabel("Salary")
plt.show()
#Visualize Polynomial Linear Regression Result
label = label.replace("|label ", "")
f_r, f_g, f_b = feature.split(" ")
predict.append([int(f_r), int(f_g), int(f_b)])
l_r, l_g, l_b, sp = label.split(" ")
ground_truth.append([
int(l_r),
int(l_g),
int(l_b),
])
return predict, ground_truth
input_X, vector = loadTrainData(train_path)
poly = PolynomialFeatures(degree=3)
X_ = poly.fit_transform(input_X)
X_ = numpy.delete(X_, (0), axis=1)
clf = linear_model.LinearRegression()
clf.fit(X_, vector)
predict, ground_truth = loadTestData(test_path)
predict_ = poly.fit_transform(predict)
predict_ = numpy.delete(predict_, (0), axis=1)
predicted = clf.predict(predict_)
predicted = [[int(round(x[0])),
int(round(x[1])),
int(round(x[2]))] for x in predicted]
from sklearn.metrics import mean_squared_error
from sklearn.metrics import r2_score
from math import sqrt
from sklearn.preprocessing import PolynomialFeatures
house_data = pd.read_csv('housing.csv')
X = pd.DataFrame(house_data['RM'])
Y = house_data['MEDV']
X_train, X_test, Y_train, Y_test = train_test_split(X,
Y,
test_size=0.20,
random_state=5)
poly_reg = PolynomialFeatures(degree=2)
X_train_2_d = poly_reg.fit_transform(X_train)
X_test_2_d = poly_reg.transform(X_test)
lin_reg = LinearRegression(normalize=True)
lin_reg.fit(X_train_2_d, Y_train)
test_pred = lin_reg.predict(X_test_2_d)
train_pred = lin_reg.predict(X_train_2_d)
rms = sqrt(mean_squared_error(Y_test, test_pred))
print(rms)
r2 = r2_score(Y_test, test_pred)
print(r2)
# data = np.loadtxt(path, dtype=float, delimiter=',',
# converters={4: iris_type})
data = pd.read_csv(path, header=None)
data[4] = pd.Categorical(data[4]).codes
# iris_types = data[4].unique()
# print iris_types
# for i, type in enumerate(iris_types):
# data.set_value(data[4] == type, 4, i)
x, y = np.split(data.values, (4, ), axis=1)
# print 'x = \n', x
# print 'y = \n', y
# 仅使用前两列特征
x = x[:, :2]
lr = Pipeline([('sc', StandardScaler()),
('poly', PolynomialFeatures(degree=3)),
('clf', LogisticRegression())])
lr.fit(x, y.ravel())
y_hat = lr.predict(x)
y_hat_prob = lr.predict_proba(x)
np.set_printoptions(suppress=True)
print 'y_hat = \n', y_hat
print 'y_hat_prob = \n', y_hat_prob
print u'准确度：%.2f%%' % (100 * np.mean(y_hat == y.ravel()))
# 画图
N, M = 500, 500 # 横纵各采样多少个值
x1_min, x1_max = x[:, 0].min(), x[:, 0].max() # 第0列的范围
x2_min, x2_max = x[:, 1].min(), x[:, 1].max() # 第1列的范围
t1 = np.linspace(x1_min, x1_max, N)
t2 = np.linspace(x2_min, x2_max, M)
x1, x2 = np.meshgrid(t1, t2) # 生成网格采样点
def PolynomialLogisticRegression(degree):
return Pipeline([('poly', PolynomialFeatures(degree=degree)),
('std_scaler', StandardScaler()),
('log_reg', LogisticRegression())])
def true_fun(X):
return np.sin(2 * np.pi * X)
np.random.seed(0)
n_samples = 30
degrees = [1, 4, 15]
X = np.sort(np.random.rand(n_samples))
y = true_fun(X) + np.random.randn(n_samples) * 0.1
plt.figure(figsize=(7, 2.5))
for i in range(len(degrees)):
ax = plt.subplot(1, len(degrees), i + 1)
plt.setp(ax, xticks=(), yticks=())
polynomial_features = PolynomialFeatures(degree=degrees[i], include_bias=False)
linear_regression = LinearRegression()
pipeline = Pipeline([("polynomial_features", polynomial_features), ("linear_regression", linear_regression)])
pipeline.fit(X[:, np.newaxis], y)
# Evaluate the models using crossvalidation
scores = cross_val_score(pipeline, X[:, np.newaxis], y, scoring="neg_mean_squared_error", cv=10)
X_test = np.linspace(0, 1, 100)
plt.plot(X_test, pipeline.predict(X_test[:, np.newaxis]), label="Model")
plt.plot(X_test, true_fun(X_test), label="True function")
plt.scatter(X, y, edgecolor='b', s=20, label="Samples")
plt.xlabel("x")
plt.ylabel("y")
plt.xlim((0, 1))
plt.ylim((-2, 2))
####################################################################################################################################################
# Linear Regression
# Fitting Linear Regression to the dataset
from sklearn.linear_model import LinearRegression
lin_reg = LinearRegression()
lin_reg.fit(X_train, y_train)
y_pred_linear = lin_reg.predict(X_test)
result_score_linear_prediction = r2_score(y_test, y_pred_linear)
print('result score for linear regression is ', result_score_linear_prediction)
####################################################################################################################################################
# Polynomial Regression
from sklearn.preprocessing import PolynomialFeatures
poly_reg = PolynomialFeatures(degree=2)
X_poly = poly_reg.fit_transform(X_train)
lin_reg_2 = LinearRegression()
lin_reg_2.fit(X_poly, y_train)
y_pred_poly = lin_reg_2.predict(poly_reg.fit_transform(X_test))
result_score_polynomial_prediction = r2_score(y_test, y_pred_linear)
print('result score for polynomial regression is ',
result_score_polynomial_prediction)
onehotEncr = OneHotEncoder(categorical_features=[0])
#onehotEncr = OneHotEncoder(categorical_features=[1])
X = onehotEncr.fit_transform(X).toarray()
labEnc_Y = LabelEncoder()
Y = labEnc_Y.fit_transform(Y)
plt.scatter(X[:,2], Y, marker='o')
"""New"""
np.random.seed(0)
poly_features = PolynomialFeatures(degree=2, include_bias=False)
X = poly_features.fit_transform(X)
model = SGDRegressor(max_iter=10000, eta0=0.001)
model.fit(X,Y)
print('Coeff R2 =', model.score(X, Y))
plt.scatter(X[:,4], Y, marker='o')
plt.scatter(X[:,0], model.predict(X), c='red', marker='+')
# Polynomial Regression
import matplotlib.pyplot as plt
import pandas as pd
# Importing the dataset
dataset = pd.read_csv('polynomial_regression.csv')
X = dataset.iloc[:, 1:2].values
y = dataset.iloc[:, 2].values
# Fitting Polynomial Regression to the dataset
from sklearn.preprocessing import PolynomialFeatures
poly_reg = PolynomialFeatures(degree=4)
X_poly = poly_reg.fit_transform(X)
from sklearn.linear_model import LinearRegression
poly_reg.fit(X_poly, y)
model = LinearRegression()
model.fit(X_poly, y)
# Visualising the Polynomial Regression results
plt.scatter(X, y, color='red')
plt.plot(X, model.predict(X_poly), color='blue')
plt.title('Polynomial Regression Example')
plt.xlabel('Position level')
plt.ylabel('Salary')
plt.show()
def analysis_7(df_Coredata):
""" 多次元多項式モデル """
#https://www.jeremyjordan.me/polynomial-regression/
X = df_Coredata[['d','e','f','g','i']]
y = df_Coredata['j']
# グラフのスタイルを指定
sns.set(style = 'whitegrid', context = 'notebook')
# 変数のペアの関係をプロット
#sns.pairplot(df_Coredata)
#plt.show()
#X_train, X_test, y_train, y_test = train_test_split(X,y,random_state = 0)
#lr = linear_model.LinearRegression().fit(X_train, y_train)
#print("Trainng set score: {:.2f}".format(lr.score(X_train, y_train)))
#print("Test set score: {:.2f}".format(lr.score(X_test, y_test)))
### データのスケール変換
# 標準化
std_Scaler = StandardScaler()
data_std = std_Scaler.fit_transform(X)
mmx_Scaler =MinMaxScaler()
X_scaled = mmx_Scaler.fit_transform(X)
#X_test_scaled = scaler.transform(X_test)
#print(X_train_scaled)
poly = PolynomialFeatures(degree = 2).fit(data_std)
print(poly.get_feature_names())
