def wage_data_linear():
X, y = wage()
gam = LinearGAM(n_splines=10)
gam.gridsearch(X, y, lam=np.logspace(-5,3,50))
XX = gam.generate_X_grid()
plt.figure()
fig, axs = plt.subplots(1,3)
titles = ['year', 'age', 'education']
for i, ax in enumerate(axs):
ax.plot(XX[:, i], gam.partial_dependence(XX, feature=i))
ax.plot(XX[:, i], *gam.partial_dependence(XX, feature=i, width=.95)[1],
c='r', ls='--')
if i == 0:
ax.set_ylim(-30,30);
ax.set_title(titles[i])
fig.tight_layout()
plt.savefig('imgs/pygam_wage_data_linear.png', dpi=300)
def wage_X_y():
# y is real
# recommend LinearGAM
return wage(return_X_y=True)
gam1.summary()
gam2 = LinearGAM(te(0, 1)).fit(X, y)
gam2.summary()
import pandas as pd
pd.DataFrame(X).corr()
######################################################
# regression
from pygam import LinearGAM, s, f
from pygam.datasets import wage
X, y = wage(return_X_y=True)
## model
gam = LinearGAM(s(0) + s(1) + f(2))
gam.gridsearch(X, y)
gam.summary()
## plotting
plt.figure()
fig, axs = plt.subplots(1, 3)
titles = ['year', 'age', 'education']
for i, ax in enumerate(axs):
XX = gam.generate_X_grid(term=i)
ax.plot(XX[:, i], gam.partial_dependence(term=i, X=XX))
ax.plot(XX[:, i],
from pygam.datasets import wage
from pygam import LinearGAM, s, f
import numpy as np
import matplotlib.pyplot as plt
X, y = wage()
gam = LinearGAM(s(0, n_splines=5) + s(1) + f(2)).fit(X, y)
gam.summary()
lam = np.logspace(-3, 5, 5)
lams = [lam] * 3
gam.gridsearch(X, y, lam=lams)
gam.summary()
lams = np.random.rand(100, 3) # random points on [0, 1], with shape (100, 3)
lams = lams * 8 - 3 # shift values to -3, 3
lams = np.exp(lams) # transforms values to 1e-3, 1e3
random_gam = LinearGAM(s(0) + s(1) + f(2)).gridsearch(X, y, lam=lams)
random_gam.summary()
print(gam.statistics_['GCV'] < random_gam.statistics_['GCV'])
for i, term in enumerate(gam.terms):
if term.isintercept:
continue
XX = gam.generate_X_grid(term=i)
def crude_strCat_to_int(ar, findex):
'''
check if feature is a string
if so replaces its unique values with an integer
coresponding to lexicographical order
'''
if isinstance(ar[0, findex], str):
ar[:, findex] = np.unique(ar[:, findex], return_inverse=True)[1]
# load dataset (as pd.DataFrame) => describe features
df = wage(return_X_y=False)
df.describe(include='all')
'''
type of terms:
1) int/category ['year']
2) int ['age']
3) continous ['logwage']
4) category ['sex','maritl','race','education','religion','jobclass','health','health_ins']
'''
#prep X and y
features = ['year', 'age', 'education']
X = df[features].values
crude_strCat_to_int(X, 2)
df = pd.DataFrame(dataset, columns=column_name)
# df1 = pd.DataFrame(dataset1, columns=column_name)
db.connect.commit()
train_value = df['2020-09-01' > df['date']]
x_train1 = train_value.iloc[:, 1:].astype('float64')
y_train1 = train_value['value'].astype('float64').to_numpy()
x_train2 = train_value['rain'].astype('float64')
from pygam import LinearGAM, s, f
from pygam.datasets import wage
x_train2, y_train1 = wage()
gam = LinearGAM(s(0) + s(1) + f(2)).fit(x_train2,
y_train1) # s(0) + s(1) + f(2)
gam.summary()
import matplotlib.pyplot as plt
for i, term in enumerate(gam.terms):
if term.isintercept:
continue
XX = gam.generate_X_grid(term=i)
pdep, confi = gam.partial_dependence(term=i, X=XX, width=0.95)
plt.figure()
plt.plot(XX[:, term.feature], pdep)