eqn = """happiness ~ -1 + freedom + family + year + economy + health + trust"""
y,x = pt.dmatrices(eqn, data=data)
# Initialize and fit the model
gam = LinearGAM(s(0) + s(1) + s(2) + s(3) + s(4) + s(5))
gam = gam.gridsearch(np.asarray(x), y)
# Specify plot shape
titles = ['freedom', 'family', 'year', 'economy',
'health', 'trust']
fig = tools.make_subplots(rows=2, cols=3, subplot_titles=titles)
fig['layout'].update(height=800, width=1200, title='pyGAM', showlegend=False)
for i, title in enumerate(titles):
XX = gam.generate_X_grid(term=i)
pdep, confi = gam.partial_dependence(term=i, width=.95)
trace = go.Scatter(x=XX[:,i], y=pdep, mode='lines', name='Effect')
ci1 = go.Scatter(x = XX[:,i], y=confi[:,0], line=dict(dash='dash', color='grey'), name='95% CI')
ci2 = go.Scatter(x = XX[:,i], y=confi[:,1], line=dict(dash='dash', color='grey'), name='95% CI')
if i<3:
fig.append_trace(trace, 1, i+1)
fig.append_trace(ci1, 1, i+1)
fig.append_trace(ci2, 1, i+1)
else:
fig.append_trace(trace, 2, i-2)
fig.append_trace(ci1, 2, i-2)
fig.append_trace(ci2, 2, i-2)
py.plot(fig)
predictors = ['SqFtTotLiving', 'SqFtLot', 'Bathrooms', 'Bedrooms', 'BldgGrade']
outcome = 'AdjSalePrice'
X = house_98105[predictors].values
y = house_98105[outcome]
## model
gam = LinearGAM(s(0, n_splines=12) + l(1) + l(2) + l(3) + l(4))
gam.gridsearch(X, y)
print(gam.summary())
fig, axes = plt.subplots(figsize=(8, 8), ncols=2, nrows=3)
titles = ['SqFtTotLiving', 'SqFtLot', 'Bathrooms', 'Bedrooms', 'BldgGrade']
for i, title in enumerate(titles):
ax = axes[i // 2, i % 2]
XX = gam.generate_X_grid(term=i)
ax.plot(XX[:, i], gam.partial_dependence(term=i, X=XX))
ax.plot(XX[:, i],
gam.partial_dependence(term=i, X=XX, width=.95)[1],
c='r',
ls='--')
ax.set_title(titles[i])
axes[2][1].set_visible(False)
plt.tight_layout()
plt.show()
## Additional material - not in book
## Regularization
### Lasso
#X[0] es el año X[0] = 0 es 2000?...
#X[1] es la edad de la persona
#X[2] es su nivel de estudios, 0 = basica, 1=media superior, 2 = universidad, 3= posgrado
#y ingresos $$
## model
gam1 = LinearGAM(s(0) + s(1) + f(2), fit_intercept=False)
gam1.gridsearch(X, y)
## plotting
plt.figure(figsize=(10, 7.5))
fig, axs = plt.subplots(1, 3)
titles = ['year', 'age', 'education']
for i, ax in enumerate(axs):
XX = gam1.generate_X_grid(term=i)
ax.plot(XX[:, i], gam1.partial_dependence(term=i, X=XX))
ax.plot(XX[:, i],
gam1.partial_dependence(term=i, X=XX, width=.95)[1],
c='r',
ls='--')
ax.set_title(titles[i])
plt.rcParams['figure.figsize'] = [10, 7.5]
XX = [[2021, 29, 4]]
print(gam1.predict(XX))
for i in range(3):
print(gam1.partial_dependence(term=i, X=XX))
## model
gam2 = LinearGAM(s(0, constraints='monotonic_inc') +
def get_graph_figure(data, atlas, spl):
fig = go.Figure()
x = data.Age.array
y = data[atlas].array
color = 'rgba(123,0,123,0.2)'
lncolor = 'rgb(123,50,123)'
gam = LinearGAM(s(0, n_splines=spl)).fit(x, y)
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)
fig.add_traces(
go.Scatter(x=XX[:, term.feature],
y=confi.T[1],
name='UPR of Total',
line=dict(dash='dash', color=lncolor),
legendgroup="total",
showlegend=False,
hovertemplate="Age: %{x} <br>Volume: %{y}"))
fig.add_traces(
go.Scatter(x=XX[:, term.feature],
y=pdep,
name='Total',
line=dict(color='black', width=3),
legendgroup="total",
fill='tonexty',
fillcolor=color,
hovertemplate="Age: %{x} <br>Volume: %{y}"))
fig.add_traces(
go.Scatter(x=XX[:, term.feature],
y=confi.T[0],
name='LWR of Total',
line=dict(dash='dash', color=lncolor),
legendgroup="total",
showlegend=False,
fill='tonexty',
fillcolor=color,
hovertemplate="Age: %{x} <br>Volume: %{y}"))
x = data[data['Sex'] == 'M'].Age.array
y = data[data['Sex'] == 'M'][atlas].array
color = 'rgba(0,0,255,0.1)'
lncolor = 'rgb(0,100,255)'
gam = LinearGAM(s(0, n_splines=spl)).fit(x, y)
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)
fig.add_traces(
go.Scatter(x=XX[:, term.feature],
y=confi.T[1],
name='UPR of Male',
line=dict(dash='dash', color=lncolor),
legendgroup="male",
showlegend=False,
visible='legendonly',
hovertemplate="Age: %{x} <br>Volume: %{y}"))
fig.add_traces(
go.Scatter(x=XX[:, term.feature],
y=pdep,
name='Male',
line=dict(color='black', width=3),
legendgroup="male",
visible='legendonly',
fill='tonexty',
fillcolor=color,
hovertemplate="Age: %{x} <br>Volume: %{y}"))
fig.add_traces(
go.Scatter(x=XX[:, term.feature],
y=confi.T[0],
name='LWR of Male',
line=dict(dash='dash', color=lncolor),
legendgroup="male",
showlegend=False,
visible='legendonly',
fill='tonexty',
fillcolor=color,
hovertemplate="Age: %{x} <br>Volume: %{y}"))
x = data[data['Sex'] == 'F'].Age.array
y = data[data['Sex'] == 'F'][atlas].array
color = 'rgba(255,0,0,0.1)'
lncolor = 'rgb(255,100,0)'
gam = LinearGAM(s(0, n_splines=spl)).fit(x, y)
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)
fig.add_traces(
go.Scatter(x=XX[:, term.feature],
y=confi.T[1],
name='UPR of Female',
line=dict(dash='dash', color=lncolor),
legendgroup="female",
showlegend=False,
visible='legendonly',
hovertemplate="Age: %{x} <br>Volume: %{y}"))
fig.add_traces(
go.Scatter(x=XX[:, term.feature],
y=pdep,
name='Female',
line=dict(color='black', width=3),
legendgroup="female",
visible='legendonly',
fill='tonexty',
fillcolor=color,
hovertemplate="Age: %{x} <br>Volume: %{y}"))
fig.add_traces(
go.Scatter(x=XX[:, term.feature],
y=confi.T[0],
name='LWR of Female',
line=dict(dash='dash', color=lncolor),
legendgroup="female",
showlegend=False,
visible='legendonly',
fill='tonexty',
fillcolor=color,
hovertemplate="Age: %{x} <br>Volume: %{y}"))
if atlas[0] == 'B':
ytitle = 'Brain Volume'
elif atlas[0] == 'R':
ytitle = 'Right ' + atlas[2:-5]
else:
ytitle = 'Left ' + atlas[2:-5]
fig.update_layout(
xaxis_title="Age",
yaxis_title=ytitle,
)
return fig
for m in range(len(y)): if y[m] >= 0 and c_user[m] >= 3: data_item_2.append([z[m], z[m]-y[m]]) data_t_.append([z[m], z[m]-y[m]]) th_90 = np.quantile(np.array(data_t_)[:, 0], 0.9) for m in range(len(y)): if y[m] >= 0 and z[m] <= th_90: data_item_3.append([z[m], z[m]-y[m]]) gam = LinearGAM(n_splines=4).fit(np.array(data_item_0)[:, 0], np.array(data_item_0)[:, 1]) XX = gam.generate_X_grid(term=0) gam_90 = LinearGAM(n_splines=4).fit(np.array(data_item_1)[:, 0], np.array(data_item_1)[:, 1]) XX_90 = gam_90.generate_X_grid(term=0) u_lim = max(max(np.array(data_item_0)[:, 0]), max(np.array(data_item_0)[:, 1])) diag = np.linspace(0, u_lim) zeros = np.linspace(0, 0) plt.figure(1); plt.plot(diag, zeros, color='black', ls='--', lw=3) plt.plot(XX, gam.predict(XX), color='r', label='X=DeepCoNN', lw=2) # plt.plot(XX_90, gam_90.predict(XX_90), color='r', ls='--', lw=3, label='Top 90% uRMSE, X=DeepCoNN') gam_mf = LinearGAM(n_splines=4).fit(np.array(data_item_2)[:, 0], np.array(data_item_2)[:, 1]) XX = gam_mf.generate_X_grid(term=0) gam_mf_90 = LinearGAM(n_splines=4).fit(np.array(data_item_3)[:, 0], np.array(data_item_3)[:, 1]) XX_90 = gam_mf_90.generate_X_grid(term=0) plt.plot(XX, gam_mf.predict(XX), color='b', label='X=MF_re', lw=2)
# # if i==0 and j==0:
# # y = dfs_test[-1].iloc[:, k].tolist()
# # else:
# # y = dfs_test[i*4+j].iloc[:, k].tolist()
z = df_mf.iloc[:, k].tolist()
for m in range(len(x)):
if x[m] >= 0 and c_user[m] >= 3:
data_dc.append([1 + z[m], z[m] - x[m]])
data_best.append([1 + z[m], z[m] - b[m]])
# if j == 0:
data_mf.append([1 + z[m], z[m] - y[m]])
gam = LinearGAM(n_splines=4).fit(
np.array(data_dc)[:, 0],
np.array(data_dc)[:, 1])
XX = gam.generate_X_grid(term=0)
# # # gam_90 = LinearGAM(n_splines=4).fit(np.array(data_item_1)[:, 0], np.array(data_item_1)[:, 1])
# # # XX_90 = gam_90.generate_X_grid(term=0)
u_lim = max(max(np.array(data_dc)[:, 0]), max(np.array(data_dc)[:, 1]))
diag = np.linspace(1, 1 + u_lim)
zeros = np.linspace(0, 0)
axes[i].scatter(np.array(data_dc)[:, 0],
np.array(data_dc)[:, 1],
s=4,
alpha=.03,
color='r')
# axes[i].scatter(np.array(data_best)[:, 0], np.array(data_best)[:, 1], s=4, alpha=.03, color='black')
axes[i].scatter(np.array(data_mf)[:, 0],
np.array(data_mf)[:, 1],
# scatter raw data
fig = px.scatter(df, x="t", y="Exp_1", trendline="ols")
# update the markers
fig.update_traces(marker=dict(size=2,
line=dict(width=2, color='DarkSlateGrey')),
selector=dict(mode='markers'))
fig.show()
#%%
# pyGAM
# train
gam = LinearGAM(s(0, constraints="monotonic_inc"),
n_splines=25).gridsearch(X_train.reshape((-1, 1)),
y_train.reshape((-1, 1)))
# predict
XX = gam.generate_X_grid(term=0, n=500)
y = gam.predict(XX)
y_pred = gam.predict(X_test)
y_CI = gam.prediction_intervals(XX, width=.95)
#%%
# plot prediction and confindence intervals
fig = go.Figure()
fig.add_trace(
go.Scatter(x=XX.reshape((-1, )),
y=y,
name="Prediction",
line=dict(color="firebrick", width=1)))
fig.add_trace(
go.Scatter(x=XX.reshape((-1, )),
y=y_CI[:, 0],
name="95% Confidence",
