def print_tables(x, score):
for title, value, d in x:
table = _df_to_simpletable(d, float_format="%.2f", index=False)
s = table.as_latex_tabular()
s = single_tabular(s, title, score)
print(s)
print('\n')
def _linear_regression_train(table,
feature_cols,
label_col,
fit_intercept=True,
is_vif=False,
vif_threshold=10):
feature_names, features = check_col_type(table, feature_cols)
label = table[label_col]
if fit_intercept == True:
features = sm.add_constant(features, has_constant='add')
lr_model_fit = sm.OLS(label, features).fit()
else:
lr_model_fit = sm.OLS(label, features).fit()
predict = lr_model_fit.predict(features)
residual = label - predict
summary = lr_model_fit.summary()
summary_tables = simple_tables2df_list(summary.tables, drop_index=True)
summary0 = summary_tables[0]
summary1 = summary_tables[1]
if type(features) != type(table):
features = pd.DataFrame(features)
if is_vif:
summary1['VIF'] = [
variance_inflation_factor(features.values, i)
for i in range(features.shape[1])
]
summary1['VIF>{}'.format(vif_threshold)] = summary1['VIF'].apply(
lambda _: 'true' if _ > vif_threshold else 'false')
summary.tables[1] = _df_to_simpletable(summary1)
summary2 = summary_tables[2]
html_result = summary.as_html()
plt.figure()
plt.scatter(predict, label)
plt.xlabel('Predicted values for ' + label_col)
plt.ylabel('Actual values for ' + label_col)
x = predict
p1x = np.min(x)
p2x = np.max(x)
plt.plot([p1x, p2x], [p1x, p2x], 'r--')
fig_actual_predict = plt2MD(plt)
plt.figure()
plt.scatter(predict, residual)
plt.xlabel('Predicted values for ' + label_col)
plt.ylabel('Residuals')
plt.axhline(y=0, color='r', linestyle='--')
fig_residual_1 = plt2MD(plt)
plt.figure()
sm.qqplot(residual, line='s')
plt.ylabel('Residuals')
fig_residual_2 = plt2MD(plt)
plt.figure()
sns.distplot(residual)
plt.xlabel('Residuals')
fig_residual_3 = plt2MD(plt)
rb = BrtcReprBuilder()
rb.addMD(
strip_margin("""
| ## Linear Regression Result
| ### Summary
|
"""))
rb.addHTML(html_result)
rb.addMD(
strip_margin("""
|
| ### Predicted vs Actual
| {image1}
|
| ### Fit Diagnostics
| {image2}
| {image3}
| {image4}
""".format(image1=fig_actual_predict,
image2=fig_residual_1,
image3=fig_residual_2,
image4=fig_residual_3)))
model = _model_dict('linear_regression_model')
model['features'] = feature_cols
model['label'] = label_col
model['coefficients'] = lr_model_fit.params
model['fit_intercept'] = fit_intercept
model['r2'] = lr_model_fit.rsquared
model['adjusted_r2'] = lr_model_fit.rsquared_adj
model['aic'] = lr_model_fit.aic
model['bic'] = lr_model_fit.bic
model['f_static'] = lr_model_fit.fvalue
model['tvalues'] = lr_model_fit.tvalues
model['pvalues'] = lr_model_fit.pvalues
model['_repr_brtc_'] = rb.get()
model['summary0'] = summary0
model['summary1'] = summary1
model['summary2'] = summary2
lr_model_fit.remove_data()
model['lr_model'] = lr_model_fit
return {'model': model}
def _linear_regression_train(table,
feature_cols,
label_col,
fit_intercept=True,
is_vif=True,
vif_threshold=10):
features = table[feature_cols]
label = table[label_col]
lr_model = LinearRegression(fit_intercept)
lr_model.fit(features, label)
predict = lr_model.predict(features)
residual = label - predict
if fit_intercept == True:
features = sm.add_constant(features)
lr_model_fit = sm.OLS(label, features).fit()
else:
lr_model_fit = sm.OLS(label, features).fit()
summary = lr_model_fit.summary()
summary_tables = simple_tables2df_list(summary.tables, drop_index=True)
summary0 = summary_tables[0]
summary1 = summary_tables[1]
if is_vif:
summary1['VIF'] = [
variance_inflation_factor(features.values, i)
for i in range(features.shape[1])
]
summary1['VIF>{}'.format(vif_threshold)] = summary1['VIF'].apply(
lambda _: 'true' if _ > vif_threshold else 'false')
summary.tables[1] = _df_to_simpletable(summary1)
summary2 = summary_tables[2]
html_result = summary.as_html()
plt.figure()
plt.scatter(predict, label)
plt.xlabel('Predicted values for ' + label_col)
plt.ylabel('Actual values for ' + label_col)
x = predict
y = np.array(label)
a = x.size
b = np.sum(x)
c = b
d = 0
for i in x:
d += +i * i
e = np.sum(y)
f = 0
for i in range(0, x.size - 1):
f += x[i] * y[i]
det = a * d - b * c
aa = (d * e - b * f) / det
bb = (a * f - c * e) / det
p1x = np.min(x)
p1y = aa + bb * p1x
p2x = np.max(x)
p2y = aa + bb * p2x
plt.plot([p1x, p2x], [p1y, p2y], 'r--')
fig_actual_predict = plt2MD(plt)
plt.figure()
plt.scatter(predict, residual)
plt.xlabel('Predicted values for ' + label_col)
plt.ylabel('Residuals')
plt.axhline(y=0, color='r', linestyle='--')
fig_residual_1 = plt2MD(plt)
plt.figure()
sm.qqplot(residual, line='s')
plt.ylabel('Residuals')
fig_residual_2 = plt2MD(plt)
plt.figure()
sns.distplot(residual)
plt.xlabel('Residuals')
fig_residual_3 = plt2MD(plt)
rb = BrtcReprBuilder()
rb.addMD(
strip_margin("""
| ## Linear Regression Result
| ### Summary
|
"""))
rb.addHTML(html_result)
rb.addMD(
strip_margin("""
|
| ### Predicted vs Actual
| {image1}
|
| ### Fit Diagnostics
| {image2}
| {image3}
| {image4}
""".format(image1=fig_actual_predict,
image2=fig_residual_1,
image3=fig_residual_2,
image4=fig_residual_3)))
model = _model_dict('linear_regression_model')
model['features'] = feature_cols
model['label'] = label_col
model['coefficients'] = lr_model_fit.params
model['r2'] = lr_model_fit.rsquared
model['adjusted_r2'] = lr_model_fit.rsquared_adj
model['aic'] = lr_model_fit.aic
model['bic'] = lr_model_fit.bic
model['f_static'] = lr_model_fit.fvalue
model['tvalues'] = lr_model_fit.tvalues
model['pvalues'] = lr_model_fit.pvalues
model['lr_model'] = lr_model
model['_repr_brtc_'] = rb.get()
model['summary0'] = summary0
model['summary1'] = summary1
model['summary2'] = summary2
return {'model': model}