def histogram_with_distributions(ax: plt.Axes, series: pd.Series, var: str):
values = series.sort_values().values
ax.hist(values, 20, density=True)
distributions = compute_known_distributions(values)
ds.multiple_line_chart(values,
distributions,
ax=ax,
title='Best fit for %s' % var,
xlabel=var,
ylabel='')
def analyse_per_metric(rules: pd.DataFrame, metric: str, metric_values: list, save_dir: str) -> list:
print(f'Analyse per {metric}...')
conf = {'avg': [], 'top25%': [], 'top10': []}
lift = {'avg': [], 'top25%': [], 'top10': []}
leverage = {'avg': [], 'top25%': [], 'top10': []}
top_conf = []
top_lift = []
top_leverage = []
nr_rules = []
for m in metric_values:
rs = rules[rules[metric] >= m]
nr_rules.append(len(rs))
conf['avg'].append(rs['confidence'].mean(axis=0))
lift['avg'].append(rs['lift'].mean(axis=0))
leverage['avg'].append(rs['leverage'].mean(axis=0))
top_conf = rs.nlargest(int(0.25*len(rs)), 'confidence')
conf['top25%'].append(top_conf['confidence'].mean(axis=0))
top_lift = rs.nlargest(int(0.25*len(rs)), 'lift')
lift['top25%'].append(top_lift['lift'].mean(axis=0))
top_leverage = rs.nlargest(int(0.25*len(rs)), 'leverage')
leverage['top25%'].append(top_leverage['leverage'].mean(axis=0))
top_conf = rs.nlargest(10, 'confidence')
conf['top10'].append(top_conf['confidence'].mean(axis=0))
top_lift = rs.nlargest(10, 'lift')
lift['top10'].append(top_lift['lift'].mean(axis=0))
top_leverage = rs.nlargest(10, 'leverage')
leverage['top10'].append(top_leverage['leverage'].mean(axis=0))
_, axs = plt.subplots(2, 2, figsize=(20, 10), squeeze=False)
ds.multiple_line_chart(metric_values, conf, ax=axs[0, 0], title=f'Avg Confidence x {metric}',
xlabel=metric, ylabel='Avg confidence')
ds.multiple_line_chart(metric_values, lift, ax=axs[0, 1], title=f'Avg Lift x {metric}',
xlabel=metric, ylabel='Avg lift')
ds.multiple_line_chart(metric_values, leverage, ax=axs[1, 0], title=f'Avg Leverage x {metric}',
xlabel=metric, ylabel='Avg leverage')
plt.savefig(save_dir + 'HFCR Pattern Mining - Association Rules analyse per ' + metric)
plot_top_rules(top_conf, 'confidence', metric, subDir)
plot_top_rules(top_lift, 'lift', metric, subDir)
plot_top_rules(top_leverage, 'leverage', metric, subDir)
return nr_rules
test_acc_values.append(test_accuracy)
if yvalues[-1] > last_best:
best = (f, d, imp)
best_model = (prd_trn_lst, prd_tst_lst)
last_best = yvalues[-1]
last_best_train = train_acc_values[-1]
best_tree = tree
values[d] = yvalues
overfit_values[f][d] = {}
overfit_values[f][d]['train'] = train_acc_values
overfit_values[f][d]['test'] = test_acc_values
ds.multiple_line_chart(min_impurity_decrease,
values,
ax=axs[0, k],
title='Decision Trees with %s criteria' % f,
xlabel='min_impurity_decrease',
ylabel='accuracy',
percentage=True)
if (count == 0): text = key
else: text = last_name + ' - ' + key
accuracies[text] = [last_best_train, last_best]
last_accuracy = last_best
print(
'Best results achieved with %s criteria, depth=%d and min_impurity_decrease=%1.5f ==> accuracy=%1.5f'
% (best[0], best[1], best[2], last_best))
fig.text(
0.5,
print('HFCR Clustering - Metric (Hierarchical) MSE vs MAE vs SC vs DB')
_, ax = plt.subplots(1, 4, figsize=(10, 3), squeeze=False)
ds.multiple_bar_chart(LINKS, values_mse, title=f'Hierarchical MSE', xlabel='metric', ylabel='MSE', ax=ax[0, 0])
ds.multiple_bar_chart(LINKS, values_mae, title=f'Hierarchical MAE', xlabel='metric', ylabel='MAE', ax=ax[0, 1])
ds.multiple_bar_chart(LINKS, values_sc, title=f'Hierarchical SC', xlabel='metric', ylabel='SC', ax=ax[0, 2], percentage=True)
ds.multiple_bar_chart(LINKS, values_db, title=f'Hierarchical DB', xlabel='metric', ylabel='DB', ax=ax[0, 3])
plt.suptitle('HFCR Clustering - Metric (Hierarchical) MSE vs MAE vs SC vs DB')
plt.savefig(subDir + 'HFCR Clustering - Metric (Hierarchical) MSE vs MAE vs SC vs DB')
"""
ds.multiple_line_chart(N_CLUSTERS,
fig_values_1,
ax=ax[0, 0],
title='K-Means',
xlabel='k',
ylabel='SC',
percentage=True)
ds.multiple_line_chart(N_CLUSTERS,
fig_values_2,
ax=ax[0, 1],
title='EM',
xlabel='k',
ylabel='SC',
percentage=True)
#ds.multiple_line_chart(EPS, fig_values_3, ax=ax[0, 2], title='EPS', xlabel='k', ylabel='SC', percentage=True)
ds.multiple_line_chart(N_CLUSTERS,
fig_values_4,
ax=ax[0, 2],
title='Hierarchical',
test_acc_values.append(test_accuracy)
if yvalues[-1] > last_best:
best = (d, f, n)
last_best = yvalues[-1]
last_best_train = train_acc_values[-1]
best_tree = rf
best_model = (prd_trn_lst, prd_tst_lst)
values[f] = yvalues
overfit_values[d][f] = {}
overfit_values[d][f]['train'] = train_acc_values
overfit_values[d][f]['test'] = test_acc_values
ds.multiple_line_chart(n_estimators,
values,
ax=axs[0, k],
title='Random Forests with max_depth=%d' %
d,
xlabel='nr estimators',
ylabel='accuracy',
percentage=True)
text = key
if (do_feature_eng): text += ' with FS'
best_accuracies[text] = [last_best_train, last_best]
print(
'Best results with depth=%d, %1.2f features and %d estimators, with accuracy=%1.2f'
% (best[0], best[1], best[2], last_best))
fig.text(
0.5,
0.03,
'Best results with depth=%d, %1.2f features and %d estimators, with accuracy=%1.2f'
best = (n, d)
last_best = yvalues[-1]
last_train_best = train_accuracy
last_best_recall = yvalues_recall[-1]
last_train_best_recall = train_recall
values[d] = yvalues
text = key
if (do_feature_eng): text += ' with FS'
best_accuracies[text] = [last_train_best, last_best]
recalls[text] = [last_train_best_recall, last_best_recall]
plt.figure()
ds.multiple_line_chart(nvalues,
values,
title='KNN variants',
xlabel='n',
ylabel='accuracy',
percentage=True)
plt.suptitle('QOT KNN - ' + key + ' - parameters')
plt.savefig(subDir + 'QOT KNN - ' + key + ' - parameters')
print('Best results with %d neighbors and %s' % (best[0], best[1]))
plt.figure()
fig, axs = plt.subplots(1, len(dist), figsize=(32, 8), squeeze=False)
i = 0
for k in range(len(dist)):
d = dist[k]
ds.multiple_line_chart(nvalues,
overfitting_values[d],
ax=axs[0, k],
title='Overfitting for dist = %s' % (d),
last_best_train, last_best
]
best_tree = gb
values[lr] = yvalues
overfitting_values[max_feat_string][d][lr] = {}
overfitting_values[max_feat_string][d][lr][
'train'] = train_acc_values
overfitting_values[max_feat_string][d][lr][
'test'] = test_acc_values
ds.multiple_line_chart(
n_estimators,
values,
ax=axs[w, k],
title=
'Gradient Boorsting with max_features=%s max_depth=%d'
% (max_feat_string, d),
xlabel='nr estimators',
ylabel='accuracy',
percentage=True)
print(
'Best results with max_features=%s, depth=%d, learning rate=%1.2f and %d estimators, with accuracy=%1.2f'
% (best[0], best[1], best[2], best[3], last_best))
fig.text(
0.5,
0.03,
'Best results with max_features=%s, depth=%d, learning rate=%1.2f and %d estimators, with accuracy=%1.2f'
% (best[0], best[1], best[2], best[3], last_best),
fontsize=7,
ha='center',
for imp in min_impurity_decrease:
tree = DecisionTreeClassifier(min_samples_leaf=1,
max_depth=d,
criterion=f,
min_impurity_decrease=imp)
tree.fit(trnX, trnY)
prdY = tree.predict(tstX)
yvalues.append(metrics.accuracy_score(tstY, prdY))
if yvalues[-1] > last_best:
best = (f, d, imp)
last_best = yvalues[-1]
best_tree = tree
values[d] = yvalues
ds.multiple_line_chart(min_impurity_decrease,
values,
ax=axs[0, k],
title='Decision Trees with %s criteria' % f,
xlabel='min_impurity_decrease',
ylabel='accuracy',
percentage=True)
plt.show()
print(
'Best results achieved with %s criteria, depth=%d and min_impurity_decrease=%1.2f ==> accuracy=%1.2f'
% (best[0], best[1], best[2], last_best))
prd_trn = best_tree.predict(trnX)
prd_tst = best_tree.predict(tstX)
ds.plot_evaluation_results(pd.unique(y), trnY, prd_trn, tstY, prd_tst)
for d in (0, 1):
mse = {}
mae = {}
for p in params:
mse_lst = []
mae_lst = []
for q in params:
mod = ARIMA(df, order=(p, d, q))
results = mod.fit()
mse_lst.append(results.mse)
mae_lst.append(results.mae)
mse[p] = mse_lst
mae[p] = mae_lst
ds.multiple_line_chart(params,
mse,
ax=axs[d, 0],
title=f'MSE with d={d}',
xlabel='p',
ylabel='mse')
ds.multiple_line_chart(params,
mae,
ax=axs[d, 1],
title=f'MAE with d={d}',
xlabel='p',
ylabel='mae')
plt.savefig(graphsDir + 'Covid19 - MSE and MAE')
def plot_forecasting(train: pd.Series,
test: pd.Series,
pred,
ax: plt.Axes = None,
rf = RandomForestClassifier(n_estimators=n,
max_depth=d,
max_features=f)
rf.fit(trnX, trnY)
prdY = rf.predict(tstX)
yvalues.append(metrics.accuracy_score(tstY, prdY))
if yvalues[-1] > last_best:
best = (d, f, n)
last_best = yvalues[-1]
best_tree = rf
values[f] = yvalues
ds.multiple_line_chart(n_estimators,
values,
ax=axs[0, k],
title='Random Forests with max_depth=%d' % d,
xlabel='nr estimators',
ylabel='accuracy',
percentage=True)
plt.show()
print(
'Best results with depth=%d, %1.2f features and %d estimators, with accuracy=%1.2f'
% (best[0], best[1], best[2], last_best))
#Performance
prd_trn = best_tree.predict(trnX)
prd_tst = best_tree.predict(tstX)
ds.plot_evaluation_results(pd.unique(y), trnY, prd_trn, tstY, prd_tst)
#ORAL TOXICITY
