def Stepwise_Forward_Selection(Data, Inputs, Output):
Model_var1 = sm.OLS
X = Data[Inputs]
y = Data[Output]
initial_list = []
threshold_in = 0.05
verbose = True
included = list(initial_list)
while True:
changed = False
excluded = list(set(X.columns) - set(included))
new_pval = pd.Series(index=excluded)
for new_column in excluded:
model = Model_var1(
y, sm.add_constant(pd.DataFrame(X[included +
[new_column]]))).fit()
new_pval[new_column] = model.pvalues[new_column]
best_pval = new_pval.min()
if best_pval < threshold_in:
best_feature = new_pval.argmin()
included.append(best_feature)
changed = True
if verbose:
print('Add {:30} with p-value {:.6}'.format(
best_feature, best_pval))
if not changed:
break
return included
def test_summary_col_ordering_preserved(self):
# gh-3767
x = [1, 5, 7, 3, 5]
x = add_constant(x)
x2 = np.concatenate([x, np.array([[3], [9], [-1], [4], [0]])], 1)
x2 = pd.DataFrame(x2, columns=['const', 'b', 'a'])
y1 = [6, 4, 2, 7, 4]
y2 = [8, 5, 0, 12, 4]
reg1 = OLS(y1, x2).fit()
reg2 = OLS(y2, x2).fit()
info_dict = {
'R2': lambda x: '{:.3f}'.format(int(x.rsquared)),
'N': lambda x: '{0:d}'.format(int(x.nobs))
}
original = actual = summary_col([reg1, reg2], float_format='%0.4f')
actual = summary_col([reg1, reg2],
regressor_order=['a', 'b'],
float_format='%0.4f',
info_dict=info_dict)
variables = ('const', 'b', 'a')
for line in str(original).split('\n'):
for variable in variables:
if line.startswith(variable):
assert line in str(actual)
def SUR_model(type):
from linearmodels.system import SUR
from collections import OrderedDict
import statsmodels.regression.linear_model as smlm
Equation = OrderedDict()
for i in range(34):
x_lag1 = np.nan * np.ones(X_data.shape[0])
y_lag1 = np.nan * np.ones(X_data.shape[0])
x_lag1[1:] = X_data.iloc[:-1, i]
y_lag1[1:] = y_data.iloc[:-1, i]
y_reg = y_data.iloc[:, i]
y_reg.name = 'netflow_' + str(i)
X_exo = pd.concat([pd.Series(y_lag1), pd.Series(x_lag1)], axis=1)
X_exo = smlm.add_constant(X_exo)
# X_exo = X_exo.iloc[1:, :]
X_exo.columns = ['const', 'netflow_lag1', 'panic']
name = 'Platform_' + str(i)
Equation[name] = {'dependent': y_reg, 'exog': X_exo}
reg = SUR(Equation).fit(method=type)
print(reg)
return reg, Equation
def test_summarycol(self):
# Test for latex output of summary_col object
desired = r'''
\begin{table}
\caption{}
\begin{center}
\begin{tabular}{lcc}
\hline
& y I & y II \\
\midrule
\midrule
const & 7.7500 & 12.4231 \\
& (1.1058) & (3.1872) \\
x1 & -0.7500 & -1.5769 \\
& (0.2368) & (0.6826) \\
\hline
\end{tabular}
\end{center}
\end{table}
'''
x = [1, 5, 7, 3, 5]
x = add_constant(x)
y1 = [6, 4, 2, 7, 4]
y2 = [8, 5, 0, 12, 4]
reg1 = OLS(y1, x).fit()
reg2 = OLS(y2, x).fit()
actual = summary_col([reg1, reg2]).as_latex()
actual = '\n%s\n' % actual
assert_equal(desired, actual)
def test_summarycol(self):
# Test for latex output of summary_col object
desired = r'''
\begin{table}
\caption{}
\begin{center}
\begin{tabular}{lcc}
\hline
& y I & y II \\
\midrule
\midrule
const & 7.7500 & 12.4231 \\
& (1.1058) & (3.1872) \\
x1 & -0.7500 & -1.5769 \\
& (0.2368) & (0.6826) \\
\hline
\end{tabular}
\end{center}
\end{table}
'''
x = [1,5,7,3,5]
x = add_constant(x)
y1 = [6,4,2,7,4]
y2 = [8,5,0,12,4]
reg1 = OLS(y1,x).fit()
reg2 = OLS(y2,x).fit()
actual = summary_col([reg1,reg2]).as_latex()
actual = '\n%s\n' % actual
assert_equal(desired, actual)
def stepwise_selection(X,
y,
initial_list=[],
threshold_in=0.01,
threshold_out=0.05,
verbose=True):
""" Perform a forward-backward feature selection based on p-values"""
included = list(initial_list)
while True:
changed = False
# forward step
excluded = list(set(X.columns) - set(included))
new_pval = pd.Series(index=excluded)
for new_column in excluded:
model = sm.OLS(
y, sm.add_constant(pd.DataFrame(X[included +
[new_column]]))).fit()
new_pval[new_column] = model.pvalues[new_column]
best_pval = new_pval.min()
if best_pval < threshold_in:
best_feature = new_pval.idxmin()
included.append(best_feature)
changed = True
if verbose:
print('Add {:30} with p-value {:.6}'.format(
best_feature, best_pval))
# backward step
model = sm.OLS(y, sm.add_constant(pd.DataFrame(X[included]))).fit()
# use all coefs except intercept
pvalues = model.pvalues.iloc[1:]
worst_pval = pvalues.max() # null if pvalues is empty
if worst_pval > threshold_out:
changed = True
worst_feature = pvalues.argmax()
included.remove(worst_feature)
if verbose:
print('Drop {:30} with p-value {:.6}'.format(
worst_feature, worst_pval))
if not changed:
break
return included
def test_OLSsummary(self):
# Test that latex output of regular OLS output still contains
# multiple tables
x = [1,5,7,3,5]
x = add_constant(x)
y1 = [6,4,2,7,4]
reg1 = OLS(y1,x).fit()
with warnings.catch_warnings():
warnings.simplefilter("ignore")
actual = reg1.summary().as_latex()
string_to_find = r'''\end{tabular}
\begin{tabular}'''
result = string_to_find in actual
assert(result is True)
def compute_QTL_gti_peaki(datapoint):
[peak_sample, gt_sample, weight_sample] = datapoint
valid_samples = np.where(gt_sample!= -1)[0]
y = np.array(peak_sample[valid_samples])
y = y.astype(float)
x = np.array(gt_sample[valid_samples])
x_weights = np.array(weight_sample[valid_samples])
x = sm.add_constant(x)
wls_model = sm.WLS(y, x, weights = x_weights)
results = wls_model.fit()
return results.pvalues[1]
def test_OLSsummary(self):
# Test that latex output of regular OLS output still contains
# multiple tables
x = [1, 5, 7, 3, 5]
x = add_constant(x)
y1 = [6, 4, 2, 7, 4]
reg1 = OLS(y1, x).fit()
with warnings.catch_warnings():
warnings.simplefilter("ignore")
actual = reg1.summary().as_latex()
string_to_find = r'''\end{tabular}
\begin{tabular}'''
result = string_to_find in actual
assert (result is True)
def test_summarycol_drop_omitted(self):
# gh-3702
x = [1, 5, 7, 3, 5]
x = add_constant(x)
x2 = np.concatenate([x, np.array([[3], [9], [-1], [4], [0]])], 1)
y1 = [6, 4, 2, 7, 4]
y2 = [8, 5, 0, 12, 4]
reg1 = OLS(y1, x).fit()
reg2 = OLS(y2, x2).fit()
actual = summary_col([reg1, reg2], regressor_order=['const', 'x1'],
drop_omitted=True)
assert 'x2' not in str(actual)
actual = summary_col([reg1, reg2], regressor_order=['x1'],
drop_omitted=False)
assert 'const' in str(actual)
assert 'x2' in str(actual)
def test_summarycol_drop_omitted(self):
# gh-3702
x = [1, 5, 7, 3, 5]
x = add_constant(x)
x2 = np.concatenate([x, np.array([[3], [9], [-1], [4], [0]])], 1)
y1 = [6, 4, 2, 7, 4]
y2 = [8, 5, 0, 12, 4]
reg1 = OLS(y1, x).fit()
reg2 = OLS(y2, x2).fit()
actual = summary_col([reg1, reg2], regressor_order=['const', 'x1'],
drop_omitted=True)
assert 'x2' not in str(actual)
actual = summary_col([reg1, reg2], regressor_order=['x1'],
drop_omitted=False)
assert 'const' in str(actual)
assert 'x2' in str(actual)
def test_summary_col_ordering_preserved(self):
# gh-3767
x = [1, 5, 7, 3, 5]
x = add_constant(x)
x2 = np.concatenate([x, np.array([[3], [9], [-1], [4], [0]])], 1)
y1 = [6, 4, 2, 7, 4]
y2 = [8, 5, 0, 12, 4]
reg1 = OLS(y1, x2).fit()
reg2 = OLS(y2, x2).fit()
info_dict = {'R2': lambda x: '{:.3f}'.format(int(x.rsquared)),
'N': lambda x: '{0:d}'.format(int(x.nobs))}
original = actual = summary_col([reg1, reg2], float_format='%0.4f')
actual = summary_col([reg1, reg2], regressor_order=['x2', 'x1'],
float_format='%0.4f',
info_dict=info_dict)
variables = ('const', 'x1', 'x2')
for line in str(original).split('\n'):
for variable in variables:
if line.startswith(variable):
assert line in str(actual)
def iteration(e0, depth):
y_star = y_data
Wald_iter_df = pd.DataFrame(index=range(depth), columns=y_star.columns)
for d in range(depth):
e = e0.sample(frac=1).reset_index(drop=True)
for i in range(34):
ei = e.iloc[:, i]
y_star_lag = pd.Series(index=y_star.index)
y_star_lag[1:] = y_star.iloc[:-1, i]
y_star.iloc[1:, i] = ei + Params_df.loc[
'const', i] + Params_df.loc[0, i] * y_star_lag[1:] # 生成y-star
# y_star.iloc[0, i] = y_data.iloc[0, i]
x_lag1 = pd.Series(index=y_star.index)
y_lag1 = pd.Series(index=y_star.index)
x_lag1[1:] = X_data.iloc[:-1, i]
y_lag1[1:] = y_star.iloc[:-1, i]
y_reg = y_star.iloc[:, i]
X_exo = pd.concat([y_lag1, x_lag1], axis=1)
X_exo = lm.add_constant(X_exo)
model = lm.OLS(y_reg, X_exo, missing='drop')
res = model.fit()
R = np.eye(len(res.params))[2]
# print(res.wald_test(R).fvalue[0][0])
# Wald_iter_df.iloc[d, i] = res.wald_test(R).fvalue[0][0]
try:
wald_i = res.wald_test(R).fvalue[0][0]
except ValueError:
Wald_iter_df.iloc[d, i] = np.nan
print(d, i, "Appear")
# print(X_exo)
else:
Wald_iter_df.iloc[d, i] = wald_i
return Wald_iter_df
def test_demo():
Wald_test_list = []
e0 = pd.DataFrame(index=X_data.index, columns=y_data.columns)
for i in range(34):
x_lag1 = np.nan * np.ones(X_data.shape[0])
y_lag1 = np.nan * np.ones(X_data.shape[0])
x_lag1[1:] = X_data.iloc[:-1, i]
y_lag1[1:] = y_data.iloc[:-1, i]
y_reg = y_data.iloc[:, i]
X_exo = pd.concat([pd.Series(y_lag1), pd.Series(x_lag1)], axis=1)
X_exo = lm.add_constant(X_exo)
model = lm.OLS(y_reg, X_exo, missing='drop')
res = model.fit()
R = np.eye(len(res.params))[2]
print(res.params)
print(R)
print(res.wald_test(R))
Params_df.iloc[:, i] = res.params
Wald_test_list.append(res.wald_test(R).fvalue[0][0]) # 计算初始样本的F-value
e0.iloc[:, i] = y_reg - res.params[
'const'] - res.params[0] * y_lag1 # 长度为34,计算残值
return e0, Wald_test_list
#============================================================================== #============================================================================== # 선형 회귀 진단 # 1. 잔차의 정규성 검정 # 2. 잔차의 자기상관계수 검정 # 3. 독립변수에 대한 condition number 계산 #============================================================================== from sklearn.datasets import make_regression from statsmodels.regression import linear_model as sm import pandas as pd X0, y, coef = make_regression(n_samples=100, n_features=1, noise=20, coef=True, random_state=0) #noise : standard deviation of the gaussian noise applied to the output. dfX0 = pd.DataFrame(X0, columns=['X1']) dfX = sm.add_constant(dfX0) # 독립변수 앞에 1을 넣어서 절편용 열을 하나 만들어준다. dfy = pd.DataFrame(y, columns=['y']) model = sm.OLS(dfy, dfX) result = model.fit() print(result.summary()) # 다중공선성(독립변수중 어떤 변수는 다른 변수들로 설명 가능한 경우, full rank가 안되게 되어 회귀계수 추정에 문제가 발생함)을 해결하는 방법 # 1. 변수 선택법으로 의존적인 변수 제거 # 2. PCA로 새로운 변수를 추출 # 3. regulize 방법론 적용 (Lasso, Ridge, ElasticNet 등) from statsmodels.datasets.longley import load_pandas import seaborn as sns import matplotlib.pyplot as plt
# Use sds to make vector of noise.
eta = random.randn(len(s)) * sds # In MatLabversion: eta = randn(size(s)).*sds;
# Pretend some data points are extreme.
eta[7]=-1
eta[8]=-3
eta[10]=-3
# Find observed values of x (with noise added).
x = m*s + c + eta
# Weighted Least Squares regression. We could find the solution using the smallest value in the Farray below also.
# Find weightings w (discount) for each data point.
vars0 = sds ** 2
w=1/vars0 # In MatLabversion: w=1./vars0
#w=ones(size(w)) # un-comment this line to get solution based on uniform noise terms.
ss = sm.add_constant(s) # In MatLabversion: ss=[ones(size(s)) s] # prepend column of ones so that solution includes intercept term.
model = sm.WLS(ss, x, weights=w) # In MatLabversion: [params,stdx,mse,S] =lscov(ss,x,w)
results = model.fit()
mest2, cest2 = results.params[0]
cest2 = cest2 + c # +c to compensate for apparent incorrect intercept returned from WLS
########
xest2 = mest2 * s + cest2 # In MatLabversion: xest2 = mest2.*s + cest2;
c0 = cest2;
m0 = mest2;
# Plot fitted line xest (=xhat in text) and data points.
fig1 = plt.figure() # ; clf;
plt.plot(s,x, 'k*', s, xest2, 'k')
plt.xlabel('Salary, ' + r'$s$' + ' (groats)'); # use trick to get italic font
plt.ylabel('Height, ' + r'$x$' + ' (feet)');
plt.xlim((0,12))
sds = sds * arange(1, 12) / 10.0
# Use noise values copied from book (based on sds above).
eta = [
-0.0023, -0.0728, 0.1104, 0.6076, -0.3034, -0.2237, 0.7407, -1.0, -3.0,
-2.4653, -3.0
]
# Find observed values of x (with noise added).
x = m * s + c + eta
# Weighted Least Squares regression.
# Find weightings w (discount) for each data point.
vars0 = sds**2
w = 1 / vars0
# Un-comment next line for solution based on un-weighted regression.
#w=ones(size(w))
ss = sm.add_constant(s) # Add column of 1s for regression.
model = sm.WLS(x, ss, weights=w)
results = model.fit()
cest2, mest2 = results.params
print('Estimated slope = %.3f,' % mest2)
print(' estimated intercept = %.3f.' % cest2)
# Make line xest2 based on fitted slope and intercept.
s2 = arange(0, 13)
xest2 = mest2 * s2 + cest2
# Plot fitted line xest, data points, and error bars.
fig1 = plt.figure()
plt.errorbar(s, x, yerr=sds, fmt='o', color='k')
plt.plot(s, x, 'k*', s2, xest2, 'k--')
plt.xlabel('Salary, $s$ (groats)')
WeekDayNo_dummies = pd.get_dummies(df['WeekDayNo']).rename(columns=lambda x: 'WeekDayNo_' + str(x))
WeekDayNo_dummies = pd.DataFrame(WeekDayNo_dummies)
df = pd.concat([df, WeekDayNo_dummies], axis=1)
df = df.drop('WeekDayNo',axis=1)
Event_dummies = pd.get_dummies(df['Event']).rename(columns=lambda x: 'Event_' + str(x))
Event_dummies = pd.DataFrame(Event_dummies)
df = pd.concat([df, Event_dummies], axis=1)
df = df.drop('Event',axis=1)
df_predictor = df[['Holiday','WeekDayNo_1','WeekDayNo_2','WeekDayNo_3','WeekDayNo_4','WeekDayNo_5','WeekDayNo_6','WeekDayNo_7']]
y_target = df['DailyLongTerm_Vessey']
df_predictor = lm.add_constant(df_predictor)
df_fit, df_eval, y_fit, y_eval= train_test_split( df_predictor, y_target, test_size=.2, random_state=1 )
ols_model = lm.OLS(y_fit,df_fit,).fit()
prediction = ols_model.predict(df_eval)
print(ols_model.summary())
prediction = pd.DataFrame(prediction)
prediction.columns = ['predicted_values']
y_eval = y_eval.reset_index(drop=True)
y_eval.columns = ['DailyLongTerm_Vessey']
RMSE = mean_squared_error(y_eval, prediction)**0.5
result_compare = pd.concat([prediction,y_eval], axis=1)
print(result_compare,RMSE)
def model(model_name, train_x, train_y, test_x,alpha = 0.1,):
summary = None
from sklearn.neural_network import MLPRegressor
from sklearn.svm import SVR
import sklearn
import statsmodels.regression.linear_model as sm
if model_name == 'Random':
test_y = pd.Series(np.random.random_sample((len(test_x),)), index=test_x.index)
if model_name == 'None':
test_y = test_x.iloc[:,0]
if model_name == 'MLPRegressor':
mlp = MLPRegressor(hidden_layer_sizes=(20, 20))
mlp.fit(train_x, train_y)
y_pred = mlp.predict(test_x)
test_y = pd.Series(y_pred, index=test_x.index)
if model_name == 'Lasso':
model = sklearn.linear_model.Lasso(0.001,fit_intercept = False)
lasso = model.fit(train_x, train_y)
test_y = pd.Series(lasso.predict(test_x), index=test_x.index)
summary = lasso.score(train_x,train_y)
if model_name == 'Ridge':
model = sklearn.linear_model.Ridge(1.0,fit_intercept = False)
ridge = model.fit(train_x, train_y)
test_y = pd.Series(ridge.predict(test_x), index=test_x.index)
summary = ridge.score(train_x, train_y)
if model_name == 'SVR':
svr_rbf = SVR(kernel='rbf', C=1, gamma=0.0001, epsilon=0.1)
svr_rbf.fit(train_x, train_y)
y_pred_rbf = svr_rbf.predict(test_x)
test_y = pd.Series(y_pred_rbf, index=test_x.index)
if model_name == 'StepWise':
feature_col = list(train_x.columns.values)
length = len(feature_col)
final_feature = []
for i in range(length):
pvalue_min = 1
column_min = ""
for feature in feature_col:
temp_feature = final_feature + [feature]
x = sm.add_constant(train_x.loc[:,temp_feature])
model = sm.OLS(train_y, x)
pvalue = model.fit().pvalues[i + 1]
# print(pvalue)
if pvalue < pvalue_min and pvalue < alpha:
pvalue_min = pvalue
column_min = feature
if column_min != "":
feature_col.remove(column_min)
final_feature.append(column_min)
else:
break
X = sm.add_constant(train_x.loc[:,final_feature])
model = sm.OLS(train_y, X)
res = model.fit()
summary = pd.Series(res.pvalues, index=['const'] + final_feature)
if ~np.isnan(res.f_pvalue):
summary['f_test'] = res.f_pvalue
if ~np.isnan(res.rsquared_adj):
summary['score'] = res.rsquared_adj
xx = sm.add_constant(test_x.loc[:,final_feature],has_constant='raise')
test_y = res.predict(xx)
if model_name == 'AdaBoost':
from sklearn.ensemble import AdaBoostRegressor
model = AdaBoostRegressor(n_estimators=100,learning_rate = 0.5)
adaboost = model.fit(train_x,train_y)
test_y = pd.Series(adaboost.predict(test_x),index = test_x.index)
if model_name == 'RandomForestRegressor':
from sklearn.ensemble import RandomForestRegressor
rfr = RandomForestRegressor(n_estimators=100, criterion='mse',max_features='auto')
rfr.fit(train_x, train_y)
y_pred_rfr = rfr.predict(test_x)
test_y = pd.Series(y_pred_rfr, index=test_x.index)
return test_y,summary
def __model(model_name, train_x, train_y, test_x,alpha = 0.1,*args,**kwargs):
summary = None
from sklearn.neural_network import MLPRegressor
from sklearn.svm import SVR
import sklearn
import statsmodels.regression.linear_model as sm
from sklearn.model_selection import TimeSeriesSplit
cv = TimeSeriesSplit(n_splits=3)
if model_name == 'Random':
test_y = pd.Series(np.random.random_sample((len(test_x),)), index=test_x.index)
if model_name == 'None':
test_y = test_x.iloc[:,0]
if model_name == 'MLPRegressor':
mlp = MLPRegressor(hidden_layer_sizes=(20, 20))
mlp.fit(train_x, train_y)
y_pred = mlp.predict(test_x)
test_y = pd.Series(y_pred, index=test_x.index)
if model_name == 'Lasso':
model = sklearn.linear_model.Lasso(0.001,fit_intercept = False)
lasso = model.fit(train_x, train_y)
test_y = pd.Series(lasso.predict(test_x), index=test_x.index)
summary = lasso.score(train_x,train_y)
# print(test_y.head())
# model = sklearn.linear_model.Lasso()
# param_grid = {'alpha':[1e-5,0.5*1e-4,1e-4,1e-3,1e-2,1e-1]}
# opt = sklearn.model_selection.GridSearchCV(model,param_grid,cv=cv)
# opt = opt.fit(train_x,train_y)
# test_y = pd.Series(opt.predict(test_x),index=test_x.index)
# summary = opt.score(train_x,train_y)
# print(opt.best_params_, summary)
if model_name == 'Ridge':
model = sklearn.linear_model.Ridge(1.0,fit_intercept = False)
ridge = model.fit(train_x, train_y)
test_y = pd.Series(ridge.predict(test_x), index=test_x.index)
summary = ridge.score(train_x, train_y)
if model_name == 'SVR':
# param_grid = {'gamma':list(1.0/k*np.array([1e-4,1e-3,1e-2])),\
# 'C':[0.01,0.05,0.25,1.25]}
# param_grid = {
# 'C':[0.002,0.01,0.05,0.25,1.25]}
# opt = sklearn.model_selection.GridSearchCV(svr_rbf,param_grid,cv=cv)
# opt = opt.fit(train_x,train_y)
# y_pred_rbf = opt.predict(test_x)
# summary = opt.score(train_x,train_y)
# print(opt.best_params_, summary)
k = len(train_x.columns)
svr_rbf = SVR(kernel='rbf', C=0.05, gamma=1.0/k*1e-4,epsilon = 0.005, max_iter = 5000)
svr_rbf = svr_rbf.fit(train_x, train_y)
y_pred_rbf = svr_rbf.predict(test_x)
test_y = pd.Series(y_pred_rbf, index=test_x.index)
summary = svr_rbf.score(train_x,train_y)
# print(test_y.head())
if model_name == 'StepWise':
feature_col = list(train_x.columns.values)
length = len(feature_col)
final_feature = []
for i in range(length):
pvalue_min = 1
column_min = ""
for feature in feature_col:
temp_feature = final_feature + [feature]
x = sm.add_constant(train_x.loc[:,temp_feature])
model = sm.OLS(train_y, x)
pvalue = model.fit().pvalues[i + 1]
# print(pvalue)
if pvalue < pvalue_min and pvalue < alpha:
pvalue_min = pvalue
column_min = feature
if column_min != "":
feature_col.remove(column_min)
final_feature.append(column_min)
else:
break
X = sm.add_constant(train_x.loc[:,final_feature])
model = sm.OLS(train_y, X)
res = model.fit()
summary = pd.Series(res.pvalues, index=['const'] + final_feature)
if ~np.isnan(res.f_pvalue):
summary['f_test'] = res.f_pvalue
if ~np.isnan(res.rsquared_adj):
summary['score'] = res.rsquared_adj
xx = sm.add_constant(test_x.loc[:,final_feature],has_constant='raise')
test_y = res.predict(xx)
if model_name == 'AdaBoost':
from sklearn.ensemble import AdaBoostRegressor
model = AdaBoostRegressor(n_estimators=100,learning_rate = 0.1)
adaboost = model.fit(train_x,train_y)
test_y = pd.Series(adaboost.predict(test_x),index = test_x.index)
summary = adaboost.score(train_x,train_y)
if model_name == 'RandomForestRegressor':
from sklearn.ensemble import RandomForestRegressor
rfr = RandomForestRegressor(n_estimators=100, criterion='mse',max_features='auto')
rfr.fit(train_x, train_y)
y_pred_rfr = rfr.predict(test_x)
test_y = pd.Series(y_pred_rfr, index=test_x.index)
return test_y,summary
# -*- coding: utf-8 -*- """ Name : c7_03_random_OLS.py Book : Python for Finance (2nd ed.) Publisher: Packt Publishing Ltd. Author : Yuxing Yan Date : 6/6/2017 email : [email protected] [email protected] """ import numpy as np import scipy as sp import statsmodels.regression.linear_model as sm n = 100 sp.random.seed(12345) y = [1, 2, 3, 4, 2, 3, 4] x1 = range(1, 8) x2 = [4, 2, -1, 4, 2, 3, 5] x3 = [0, 2, 3, 4, 2, 4, -1] x = [x1, x2, x3] x = sm.add_constant(x) #est = sm.OLS(formula='Sales ~ TV + Radio', data=df_adv).fit() results = sm.OLS(y, x1).fit() print(results.summary())
#%%
#FIRST DATASET REGRESSIONS
#Regression by Asset Class on all Indicators
start_date, end_date = "2000 01 01", "2008 01 01"
Y_assets = data_returns(asset_classes, start_date, end_date, "M", 1)
X_macro = data_lagged(
macro_data[[
"Monetary Policy", "International Trade", "Risk Sentiment", "Growth",
"Inflation"
]], start_date, end_date, "M", 1)
# regression on each asset class
for asset in Y_assets.columns:
res = sm.OLS(Y_assets[asset], sm.add_constant(X_macro)).fit()
print(res.summary())
#%%
start_date, end_date = "1990 01 01", "2008 01 01"
Y_assets = data_returns(asset_classes, start_date, end_date, "M", 1)
X_macro = data_lagged(
macro_data[[
"Monetary Policy", "International Trade", "Risk Sentiment", "Growth",
"Inflation"
]], start_date, end_date, "M", 1)
#Regression Per Indicator
for asset in Y_assets.columns:
xx = np.linspace(-10, 10, 1000)
plt.plot(xx, (1 / (1 + np.exp(-xx))) * 2 - 1, label='logistic (scaled)')
plt.plot(xx, np.tanh(xx), label='tanh')
plt.legend(loc=2)
plt.show()
#sklearn logistic regression
from sklearn.datasets import make_classification
import statsmodels.regression.linear_model as sm
X0, y = make_classification(n_features=1,
n_redundant=0,
n_informative=1,
n_clusters_per_class=1,
random_state=4)
X = sm.add_constant(X0)
from sklearn.linear_model import LogisticRegression
model = LogisticRegression().fit(X0, y)
import matplotlib as mpl
xx = np.linspace(-3, 3, 100)
sigm = 1.0 / (1 + np.exp(-model.coef_[0][0] * xx - model.intercept_[0]))
plt.plot(xx, sigm)
plt.scatter(X0, y, marker='o', c=y,
s=100) #(X0,y) 점들을 찍고, 형태는 o이고, 색은 y값에 따라, 사이즈는 100
plt.scatter(X0,
model.predict(X0),
marker='x',
c=y,
s=200,
