def example_trajs():
print('Generowanie i zapisywanie przykładowych trajektorii...')
path = 'data/part0/example_traj'
dirmake(path)
logg('Generowanie przykładowych trajektorii - start')
AD = andi.andi_datasets()
for model in range(5):
try:
dataset = AD.create_dataset(100, 1, [0.7], [model], 2)
except:
dataset = AD.create_dataset(100, 1, [1.7], [model], 2)
x = dataset[0][2:102]
y = dataset[0][102:]
plt.figure(figsize=(2, 2))
plt.cla()
plt.gca().spines['top'].set_visible(False)
plt.gca().spines['right'].set_visible(False)
plt.xlabel('x')
plt.ylabel('y')
plt.title(AD.avail_models_name[model], loc='left')
plt.plot(x, y, color=colors[model], linewidth=2, alpha=0.5)
plt.scatter(x,
y,
c=range(len(x)),
cmap=color_maps[model],
marker='.',
s=100)
plt.savefig(path + '/' + str(AD.avail_models_name[model]) + '.pdf',
transparent=True,
bbox_inches='tight',
dpi=300)
logg('Generowanie przykładowych trajektorii - stop')
print(' --- ZAKOŃCZONO')
def TAMSD_estimation(trajectories, exps, part, Model):
global liczydlo
if part == 0:
D, real_exp, est_exp, tamsds = TAMSD_estimation_traj(
0, 1, [exps, trajectories])
return D, real_exp, est_exp, tamsds
if part >= 1:
print('Obliczanie estymacji TAMSDS...')
if part in [1, 2, 3, 4, 5, 6]:
trajectories = trajectories[:-number_to_learn]
else:
trajectories = trajectories[:-floor(10**(part - 6))]
liczydlo = 0
traj_num = len(trajectories)
traj_info = pd.DataFrame(columns=['D', 'expo', 'expo_est', 'tamsds'],
index=range(traj_num))
# 2 argumenty iterwane do poola
give = []
logg('TAMSD - estymacja - start')
start = datetime.now()
for i in range(traj_num):
give.append([exps[i], trajectories[i]])
with mp.Pool(3) as pool:
temp = partial(TAMSD_estimation_traj, part, traj_num)
result = pool.map(temp, give)
pool.close()
pool.join()
print(' --- ZAKOŃCZONO')
print('Translacja wyników TAMSD...')
liczydlo = 0
for i in result:
traj_info.loc[liczydlo] = i
liczydlo += 1
if liczydlo % 500 == 0:
print(f'TAMSD - translacja - {liczydlo}/{traj_num}')
stop = datetime.now()
logg(f'TAMSD - estymacja - koniec {stop - start}')
print(' --- ZAKOŃCZONO')
path = f'data/part{part}/model{Model}/TAMSD/'
dirmake(path)
fname = path + str('estimated.csv')
print(f'Zapisywanie wyników do pliku {fname}')
traj_info.to_csv(fname)
print(' --- ZAKOŃCZONO')
def get_features(trajectories, exps, part, Model):
if part >= 1:
print('Wyciąganie parametrów z trajektorji...')
global l_t
### odczyt danych z trajektorii
l_t = 0
traj_num = len(trajectories)
# 2 argumenty iterwane do poola
give = []
logg('ML - wyciąganie danych - start')
start = datetime.now()
for i in range(traj_num):
give.append([exps[i], trajectories[i]])
with mp.Pool(3) as pool:
temp = partial(get_info, 5, traj_num)
result = pool.map(temp, give)
pool.close()
pool.join()
### zapis do pandas
traj_info = pd.DataFrame(columns=[
'alpha', 'diffusivity', 'efficiency', 'slowdown', 'MSD_ratio1',
'MSD_ratio5', 'antigaussinity1', 'antigaussinity5', 'straigthness',
'autocorrelation1', 'autocorrelation5', 'max_distance',
'trappedness', 'fractal_dim'
],
index=range(traj_num))
l_t = 0
for traj in result:
traj_info.loc[l_t] = traj
l_t += 1
if l_t % 500 == 0:
print(f'translacja - {l_t}/{traj_num}')
stop = datetime.now()
logg(f'ML - wyciąganie danych - koniec {stop - start}')
# zapis do pliku
path = f'data/part{part}/model{Model}/ML'
dirmake(path)
fname = f'data/part{part}/model{Model}/ML/features.csv'
print(f'Zapisywanie danych do pliku {fname}')
traj_info.to_csv(fname)
print(' --- ZAKOŃCZONO')
return traj_info
Q_generate_plot = int(input("Ile trajektorii zapisać w postaci graficznej: "))
Q_TAMSD = input("Czy chcesz przeliczyć TAMSD? (Y/n): ")
Q_TAMSD_plot = int(input("Ile obliczonych TAMSD chcesz zapisać w postaci graficznej: "))
Q_ML_features = input("Czy chcesz wyciągnąć paramtry trajektorii do ML? (Y/n): ")
Q_ML_linreg = input("Czy chcesz użyć wielowymiarowej regresji liniowej? (Y/n): ")
Q_ML_dectree = input("Czy chcesz użyć decision tree? (Y/n): ")
Q_ML_randomforest = input("Czy chcesz użyć random forest? (Y/n): ")
Q_ML_gradientboosting = input("Czy chcesz użyć gradient boosting? (Y/n): ")
logg(f'Wybrane decyzje: {Q_generate}, {Q_generate_plot}, {Q_TAMSD}, {Q_TAMSD_plot}'+
f', {Q_ML_features}, {Q_ML_linreg}, {Q_ML_dectree}, {Q_ML_randomforest}, {Q_ML_gradientboosting}.')
print(64 * '-')
N = N_long
path = f'data/part{part}/model{Model}/'
dirmake(path)
traject_loaded = False
expo_loaded = False
features_loaded = False
if Q_generate == 'Y':
# generowanie trajektorii
generate_trajectories(N, part, Model)
print(64 * '-')
if Q_generate_plot > 0:
# rysowanie trajektorii
if not traject_loaded:
trajectories = read_trajectories(part, Model)
traject_loaded = True
print(f'Tworzenie {Q_generate_plot} wykresów...')
def decision_tree(features, part, Model):
if part in [0, 1, 2, 3, 4, 5, 6]:
train_data, train_labels, test_data, test_label = split_data(
features, number_to_learn)
else:
train_data, train_labels, test_data, test_label = split_data(
features, floor(10**(part - 6)))
hiperparam_data = train_data[:floor(number_to_learn / 10)]
hiperparam_labels = train_labels[:floor(number_to_learn / 10)]
print('Wyznaczanie drzewa decyzyjnego...')
max_depth = list(range(2, 20, 1))
min_samples_split = list(range(1, 11))
min_samples_leaf = list(range(1, 6))
max_features = ['auto', 'sqrt']
random_grid = {
'max_depth': max_depth,
'min_samples_split': min_samples_split,
'min_samples_leaf': min_samples_leaf,
'max_features': max_features
}
log(f'ML - drzewo decyzyjne - szukanie superparametrów - start')
start = datetime.now()
model = DecisionTreeRegressor()
model = RandomizedSearchCV(estimator=model,
param_distributions=random_grid,
n_iter=30,
cv=3,
verbose=2,
random_state=42,
n_jobs=3,
return_train_score=True,
refit=True)
model = model.fit(hiperparam_data, hiperparam_labels)
stop = datetime.now()
log(f'ML - drzewo decyzyjne - szukanie superparametrów - koniec {stop - start}'
)
model_params = pd.DataFrame(model.best_params_, index=['decision tree'])
dirmake(f'data/part{part}/model{Model}/ML/decision_tree')
model_params.to_csv(
f'data/part{part}/model{Model}/ML/decision_tree/model_params.csv')
model = DecisionTreeRegressor(**model.best_params_)
log(f'ML - drzewo decyzyjne - nauczanie - start')
start = datetime.now()
model.fit(train_data, train_labels)
stop = datetime.now()
log(f'ML - drzewo decyzyjne - nauczanie - koniec {stop - start}')
print(' --- ZAKOŃCZONO')
path = f'data/part{part}/model{Model}/ML/decision_tree/model.pk1'
print('Zapisywanie modelu do pliku {}'.format(path))
save_model(model, path)
plt.cla()
plt.figure(figsize=(10, 6.5))
plot_tree(model,
max_depth=3,
feature_names=list(test_data),
fontsize=10,
filled=True)
path = f'data/part{part}/model{Model}/ML/decision_tree/tree.pdf'
plt.savefig(path, transparent=True, bbox_inches='tight')
plt.cla()
plt.figure(figsize=(15, 15))
plot_tree(model, feature_names=list(test_data), filled=True)
path = f'data/part{part}/model{Model}/ML/decision_tree/full_tree.pdf'
plt.savefig(path, transparent=True, bbox_inches='tight')
print(' --- ZAKOŃCZONO')
print('Testowanie modelu drzewa decyzyjnego...')
log(f'ML - drzewo decyzyjne - przewidywanie - start')
start = datetime.now()
predicted_labels = model.predict(test_data)
stop = datetime.now()
log(f'ML - drzewo decyzyjne - przewidywanie - koniec {stop - start}')
print(' --- ZAKOŃCZONO')
print('Translacja przewidywań...')
results = pd.DataFrame({'expo': test_label, 'expo_est': predicted_labels})
print(' --- ZAKOŃCZONO')
print('Translacja wyników do pliku...')
results.to_csv(
f'data/part{part}/model{Model}/ML/decision_tree/estimated.csv')
print(' --- ZAKOŃCZONO')
def save_model(model, path):
dirmake('/'.join(path.split('/')[:-1]))
with open(path, 'wb') as f:
dump(model, f)
def gradient_boosting(features, part, Model):
if part in [0, 1, 2, 3, 4, 5, 6]:
train_data, train_labels, test_data, test_label = split_data(
features, number_to_learn)
else:
train_data, train_labels, test_data, test_label = split_data(
features, floor(10**(part - 6)))
hiperparam_data = train_data[:floor(number_to_learn / 10)]
hiperparam_labels = train_labels[:floor(number_to_learn / 10)]
print('Wyznaczanie modelu gradient boosting...')
# https://towardsdatascience.com/hyperparameter-tuning-the-random-forest-in-python-using-scikit-learn-28d2aa77dd74
learning_rate = [0.001 * i for i in range(1, 21)]
n_estimators = list(range(100, 1001, 100))
max_depth = list(range(2, 20, 1))
min_samples_split = list(range(2, 11))
min_samples_leaf = list(range(1, 6))
max_features = ['auto', 'sqrt']
random_grid = {
'learning_rate': learning_rate,
'n_estimators': n_estimators,
'max_depth': max_depth,
'min_samples_split': min_samples_split,
'min_samples_leaf': min_samples_leaf,
'max_features': max_features
}
model = GradientBoostingRegressor()
log(f'ML - wzmocnienie gradientowe - szukanie superparametrów - start')
start = datetime.now()
model = RandomizedSearchCV(estimator=model,
param_distributions=random_grid,
n_iter=30,
cv=3,
verbose=2,
random_state=42,
n_jobs=3,
return_train_score=True,
refit=True)
model.fit(hiperparam_data, hiperparam_labels)
stop = datetime.now()
log(f'ML - wzmocenienie gradientowe - szukanie superparametrów - koniec {stop - start}'
)
model_params = pd.DataFrame(model.best_params_,
index=['gradient boosting'])
dirmake(f'data/part{part}/model{Model}/ML/gradient_boosting')
model_params.to_csv(
f'data/part{part}/model{Model}/ML/gradient_boosting/model_params.csv')
model = GradientBoostingRegressor(**model.best_params_)
# params = pd.read_csv(f'data/part{part}/model{Model}/ML/gradient_boosting/model_params.csv', index_col='Unnamed: 0')
# params = params.to_dict(orient = 'list')
# for key,value in params.items():
# params[key] = value[0]
# model = GradientBoostingRegressor(**params)
log(f'ML - wzmocnienie gradientowe - nauczanie - start')
start = datetime.now()
model.fit(train_data, train_labels)
stop = datetime.now()
log(f'ML - wzmocenienie gradientowe - nauczanie - koniec {stop - start}')
print(' --- ZAKOŃCZONO')
path = f'data/part{part}/model{Model}/ML/gradient_boosting/model.pk1'
print('Zapisywanie modelu do pliku {} oraz jego parametrów'.format(path))
save_model(model, path)
print(' --- ZAKOŃCZONO')
print('Testowanie modelu gradient boosting...')
log(f'ML - wzmocnienie gradientowe - przewidywanie - start')
start = datetime.now()
predicted_labels = model.predict(test_data)
stop = datetime.now()
log(f'ML - wzmocenienie gradientowe - przewidywanie - koniec {stop - start}'
)
print(' --- ZAKOŃCZONO')
print('Translacja przewidywań...')
results = pd.DataFrame({'expo': test_label, 'expo_est': predicted_labels})
print(' --- ZAKOŃCZONO')
print('Zapisywanie wyników do pliku...')
results.to_csv(
f'data/part{part}/model{Model}/ML/gradient_boosting/estimated.csv')
print(' --- ZAKOŃCZONO')
def random_forest(features, part, Model):
if part in [0, 1, 2, 3, 4, 5, 6]:
train_data, train_labels, test_data, test_label = split_data(
features, number_to_learn)
else:
train_data, train_labels, test_data, test_label = split_data(
features, floor(10**(part - 6)))
hiperparam_data = train_data[:floor(number_to_learn / 10)]
hiperparam_labels = train_labels[:floor(number_to_learn / 10)]
print('Wyznaczanie modelu random forest...')
# https://towardsdatascience.com/hyperparameter-tuning-the-random-forest-in-python-using-scikit-learn-28d2aa77dd74
n_estimators = list(range(100, 1001, 100))
max_depth = list(range(2, 20, 1))
min_samples_split = list(range(2, 11))
min_samples_leaf = list(range(1, 6))
max_features = ['auto', 'sqrt']
max_samples = [0.1 * i for i in range(1, 10)]
random_grid = {
'n_estimators': n_estimators,
'max_depth': max_depth,
'min_samples_split': min_samples_split,
'min_samples_leaf': min_samples_leaf,
'max_features': max_features,
'max_samples': max_samples
}
model = RandomForestRegressor(bootstrap=True, max_samples=0.5)
log(f'ML - las losowy - szukanie superparametrów - start')
start = datetime.now()
model = RandomizedSearchCV(estimator=model,
param_distributions=random_grid,
n_iter=30,
cv=3,
verbose=2,
random_state=42,
n_jobs=3,
return_train_score=True,
refit=True)
model.fit(hiperparam_data, hiperparam_labels)
stop = datetime.now()
log(f'ML - las losowy - szukanie superparametrów - koniec {stop - start}')
model_params = pd.DataFrame(model.best_params_, index=['random forest'])
dirmake(f'data/part{part}/model{Model}/ML/random_forest')
model_params.to_csv(
f'data/part{part}/model{Model}/ML/random_forest/model_params.csv')
log(f'ML - las losowy - nauczanie - start')
start = datetime.now()
model = RandomForestRegressor(**model.best_params_)
model.fit(train_data, train_labels)
stop = datetime.now()
log(f'ML - las losowy - nauczanie - koniec {stop - start}')
print(' --- ZAKOŃCZONO')
path = f'data/part{part}/model{Model}/ML/random_forest/model.pk1'
print('Zapisywanie modelu do pliku {} oraz jego parametrów'.format(path))
save_model(model, path)
print(' --- ZAKOŃCZONO')
print('Testowanie modelu random forest...')
log(f'ML - las losowy - przewidywanie - start')
start = datetime.now()
predicted_labels = model.predict(test_data)
stop = datetime.now()
log(f'ML - las losowy - przewidywanie - koniec {stop - start}')
print(' --- ZAKOŃCZONO')
print('Translacja przewidywań...')
results = pd.DataFrame({'expo': test_label, 'expo_est': predicted_labels})
print(' --- ZAKOŃCZONO')
print('Zapisywanie wyników do pliku...')
results.to_csv(
f'data/part{part}/model{Model}/ML/random_forest/estimated.csv')
print(' --- ZAKOŃCZONO')
def plot_noisy3():
normal_models = {}
path_results = 'data/part7-10/'
dirmake(path_results)
R2s = {}
MAEs = {}
MSEs = {}
for model in models:
R2 = []
MAE = []
MSE = []
for part in parts:
path_table = 'data/part7-10/results/part' + str(
part) + '/table.csv'
table = pd.read_csv(path_table, index_col='Unnamed: 0')
R2.append(table.loc[model.replace('_', ' ')]['R^2'])
MAE.append(table.loc[model.replace('_', ' ')]['MAE'])
MSE.append(table.loc[model.replace('_', ' ')]['MSE'])
R2s[model] = R2
MAEs[model] = MAE
MSEs[model] = MSE
for stat in ['R2', 'MAE', 'MSE']:
statistica = eval(stat)
plt.clf()
plt.figure(figsize=(4, 4))
plt.semilogx([10, 100, 1000, 10000, 100000],
statistica,
label=stat)
plt.title(model, loc='left')
plt.xticks([10, 100, 1000, 10000, 100000])
plt.yticks(statistica)
dirmake(path_results + '/' + stat + '/')
plt.savefig(path_results + stat + '/' + model + '.pdf')
for stat in ['R2', 'MAE', 'MSE']:
statistica = eval(stat + 's')
path_result = path_results + stat + '.pdf'
plt.close('all')
plt.figure(figsize=(3, 3))
n = 0
for key, value in statistica.items():
if stat == 'R2':
plt.semilogx([10, 100, 1000, 10000, 100000],
value,
label=key.replace('_', ' '),
c=colors[n + 1],
marker='x')
else:
plt.loglog([10, 100, 1000, 10000, 100000],
value,
label=key.replace('_', ' '),
c=colors[n],
marker='x')
n += 1
plt.xticks([10, 100, 1000, 10000, 100000])
if stat == 'MSE':
plt.legend(loc='center left', bbox_to_anchor=(1.05, 0.5))
plt.title(stat, loc='left')
plt.savefig(path_result,
transparent=True,
bbox_inches='tight',
dpi=300)
def test_models2(part, part_test, num_of_learning=100000, mode='full'):
''' Do testowania modelu z częsi 1 do danych z części 3-6 i do testowania modelu\
z części 3 na danych z części 1 i do testowania modeli części 7-10 na części 1'''
Model = 'A'
tests = 'A'
if part == 1:
if part_test in [3, 4, 5, 6]:
path_results = f'data/part1-6/results/part' + str(part_test) + '/'
path_estimate = f'data/part1-6/estimations/part' + str(
part_test) + '/'
elif part == 3:
if part_test == 1:
path_results = f'data/part3-1/results/part' + str(part_test) + '/'
path_estimate = f'data/part3-1/estimations/part' + str(
part_test) + '/'
if part in [1, 7, 8, 9, 10]:
if part_test == 1:
path_results = f'data/part7-10/results/part' + str(part) + '/'
path_estimate = f'data/part7-10/estimations/part' + str(part) + '/'
dataset = read_ML_features(part_test, tests)
if not 'no_gen' in mode:
trajectories = read_trajectories(part_test, tests, 'end',
num_of_learning) # to test
else:
trajectories = 'trajectories'
_, _, test_data, test_label = split_data(dataset, num_of_learning)
test_label = list(test_label)
dirmake(path_results)
dirmake(path_estimate)
models = [
'TAMSD', 'linear_regression', 'decision_tree', 'random_forest',
'gradient_boosting'
]
ttable = pd.DataFrame()
err = {}
plt.figure(figsize=(2, 2))
for model in models:
# # # estymowanie parametrów
if model == 'TAMSD':
estimated_label, test_labels = estimate(trajectories, test_label,
part, Model, tests,
'TAMSD', 100000, part_test)
else:
estimated_label, test_labels = estimate(test_data, test_label,
part, Model, tests, model,
100000, part_test)
# # # określanie mocy
table, er = test_model(estimated_label, test_labels,
model.replace('_', ' '), path_results, mode)
if 'full' in mode or 'table' in mode:
ttable = pd.concat([ttable, table])
err[model] = er
print(f'Zrobione {Model} - {tests} - {model}')
# # # rysowanki
if 'full' in mode or 'table' in mode:
print(f'Zapisywanie tabeli do pliku {path_results+"table.csv"}')
ttable.to_csv(path_results + 'table.csv')
print(f'Zrobione tabele dla {Model}-{tests}')
if 'full' in mode or 'plot' in mode:
# box plot
plt.clf()
plt.figure(figsize=(5, 5))
box = plt.boxplot(labels=err.keys(),
x=err.values(),
patch_artist=True,
notch=True,
vert=True)
colors = ['lightblue', 'orange', 'lightgreen', 'pink', 'violet']
for plott, color in zip(box['boxes'], colors):
print(plott)
plott.set_facecolor(color)
plt.savefig(path_results + 'boxplots.pdf',
transparent=True,
bbox_inches='tight',
dpi=300)
# displots
plt.clf()
sns.displot(err, common_norm=False, stat="density")
plt.plot([0, 0], [0, 1.3], color='black')
plt.savefig(path_results + 'displot1.pdf',
transparent=True,
bbox_inches='tight',
dpi=300)
plt.clf()
sns.displot(err,
kind="kde",
common_norm=False,
bw_adjust=0.7,
fill=True)
plt.plot([0, 0], [0, 1.3], color='black')
plt.savefig(path_results + 'displot2.pdf',
transparent=True,
bbox_inches='tight',
dpi=300)
plt.clf()
sns.displot(err, kind="kde", common_norm=False, bw_adjust=2)
plt.plot([0, 0], [0, 1.3], color='black')
plt.savefig(path_results + 'displot3.pdf',
transparent=True,
bbox_inches='tight',
dpi=300)
plt.clf()
sns.displot(err, kind="ecdf")
plt.plot([0, 0], [0, 1.3], color='black')
plt.savefig(path_results + 'displot4.pdf',
transparent=True,
bbox_inches='tight',
dpi=300)
print(f'Zrobione wykresy dla {Model}-{tests}')
def estimate(test_data,
test_label,
part,
Model,
Model_test,
model,
learning_number=100000,
part_test=None):
if part_test == None:
part_test = part
path_estimations = f'data/part{part}/estimations/model{Model}/test{Model_test}/{model}.csv'
dirmake(f'data/part{part}/estimations/model{Model}/test{Model_test}/')
elif part_test >= 3:
path_estimations = f'data/part1-6/estimations/part{part_test}/{model}.csv'
dirmake(f'data/part1-6/estimations/part{part_test}/')
elif part_test == 1:
if part == 3:
path_estimations = f'data/part3-1/estimations/part{part_test}/{model}.csv'
dirmake(f'data/part3-1/estimations/part{part_test}/')
elif part in [1, 7, 8, 9, 10]:
path_estimations = f'data/part7-10/estimations/part{part}/{model}.csv'
dirmake(f'data/part7-10/estimations/part{part}/')
if isfile(path_estimations):
results = pd.read_csv(path_estimations, index_col='Unnamed: 0')
else:
if model == 'TAMSD':
print('Obliczanie estymacji TAMSDS...')
logg('TAMSD - estymacja - start')
start = datetime.now()
traj_num = len(test_label)
give = []
for i in range(traj_num):
give.append([test_label[i], test_data[i]])
with mp.Pool(3) as pool:
temp = partial(TAMSD_estimation_traj, part, traj_num)
result = pool.map(temp, give)
pool.close()
pool.join()
stop = datetime.now()
logg(f'TAMSD - estymacja - koniec {stop - start}')
print(' --- ZAKOŃCZONO')
print('Translacja wyników TAMSD...')
results = pd.DataFrame(columns=['D', 'expo', 'expo_est', 'tamsds'],
index=range(traj_num))
liczydlo = 0
for i in result:
results.loc[liczydlo] = i
liczydlo += 1
print(' --- ZAKOŃCZONO')
results.to_csv(path_estimations)
else:
path_model = f'data/part{part}/model{Model}/ML/{model}/model.pk1'
print('Ładowanie modelu ...')
model = load_model(path_model)
print(' --- ZAKOŃCZONO')
print(f'Testowanie modelu {model}...')
logg(f'ML - {model} - przewidywanie - start')
start = datetime.now()
predicted_labels = model.predict(test_data)
stop = datetime.now()
logg(f'ML - {model} - przewidywanie - koniec {stop - start}')
print(' --- ZAKOŃCZONO')
print('Translacja przewidywań...')
print(len(test_label))
results = pd.DataFrame({
'expo': test_label,
'expo_est': predicted_labels
})
print(' --- ZAKOŃCZONO')
print(f'Zapisywanie wstymacji wyników do pliku - model {model}...')
results.to_csv(path_estimations)
print(' --- ZAKOŃCZONO')
print(64 * '-')
results = results.dropna()
return list(results['expo_est']), list(results['expo'])
def test_models(part, Model, num_of_learning=100000, tests=None, mode='full'):
if tests == None:
tests = Model
if part >= 1:
path_results = f'data/part{part}/results/model{Model}/test{tests}/'
path_estimate = f'data/part{part}/estimations/model{Model}/test{tests}/'
dataset = read_ML_features(part, tests)
if not 'no_gen' in mode:
trajectories = read_trajectories(part, tests, 'end',
num_of_learning)
else:
trajectories = 'trajectories'
_, _, test_data, test_label = split_data(dataset, num_of_learning)
test_label = list(test_label)
dirmake(path_results)
dirmake(path_estimate)
models = [
'TAMSD', 'linear_regression', 'decision_tree', 'random_forest',
'gradient_boosting'
]
ttable = pd.DataFrame(
columns=['R^2', 'eps = 0.05', 'eps = 0.025', 'max_error'])
err = {}
plt.figure(figsize=(2, 2))
for model in models:
# # # estymowanie parametrów
if model == 'TAMSD':
estimated_label, test_labels = estimate(
trajectories, test_label, part, Model, tests, 'TAMSD')
else:
estimated_label, test_labels = estimate(
test_data, test_label, part, Model, tests, model)
# # # określanie mocy
table, er = test_model(estimated_label, test_labels,
model.replace('_', ' '), path_results, mode)
if 'full' in mode or 'table' in mode:
ttable = pd.concat([ttable, table])
err[model] = er
print(f'Zrobione {Model} - {tests} - {model}')
# # # rysowanki
if 'full' in mode or 'table' in mode:
print(f'Zapisywanie tabeli do pliku {path_results+"table.csv"}')
ttable.to_csv(path_results + 'table.csv')
print(f'Zrobione tabele dla {Model}-{tests}')
if 'full' in mode or 'plot' in mode:
# box plot
plt.clf()
plt.figure(figsize=(5, 5))
labels = ['TAMSD', 'LR', 'DT', 'RF', 'GB']
box = plt.boxplot(labels=labels,
x=err.values(),
patch_artist=True,
notch=True,
vert=True)
colors = ['lightblue', 'orange', 'lightgreen', 'pink', 'violet']
for plott, color in zip(box['boxes'], colors):
print(plott)
plott.set_facecolor(color)
plt.savefig(path_results + 'boxplots.pdf',
transparent=True,
bbox_inches='tight',
dpi=300)
# displots
plt.clf()
sns.displot(err, common_norm=False, stat="density")
plt.plot([0, 0], [0, 1.3], color='black')
plt.savefig(path_results + 'displot1.pdf',
transparent=True,
bbox_inches='tight',
dpi=300)
plt.clf()
sns.displot(err,
kind="kde",
common_norm=False,
bw_adjust=0.7,
fill=True)
plt.plot([0, 0], [0, 1.3], color='black')
plt.savefig(path_results + 'displot2.pdf',
transparent=True,
bbox_inches='tight',
dpi=300)
plt.clf()
sns.displot(err, kind="kde", common_norm=False, bw_adjust=2)
plt.plot([0, 0], [0, 1.3], color='black')
plt.savefig(path_results + 'displot3.pdf',
transparent=True,
bbox_inches='tight',
dpi=300)
plt.clf()
sns.displot(err, kind="ecdf")
plt.plot([0, 0], [0, 1.3], color='black')
plt.savefig(path_results + 'displot4.pdf',
transparent=True,
bbox_inches='tight',
dpi=300)
print(f'Zrobione wykresy dla {Model}-{tests}')
def example_TAMSD():
print('Generowanie i zapisywanie przykładowych TAMSD...')
path = 'data/part0/example_TAMSD'
dirmake(path)
logg('Generowanie przykładowych TAMSD - start')
AD = andi.andi_datasets()
dataset = AD.create_dataset(200, 1, [0.7], [2], 2)
x = dataset[0][2:202]
y = dataset[0][202:]
trajectory = [x, y]
D, expo, expo_est, tamsds = TAMSD_estimation(trajectory, 0.7, 0, 'A')
tamsds = tamsds[:100]
t = range(1, len(tamsds) + 1)
expo_est = estimate_expo(t, tamsds, D, 100)
plt.cla()
plt.figure(figsize=(3, 3))
plt.plot(t, tamsds, '.', label='punkty TAMSD')
plt.plot(t, [4 * D * i**expo_est for i in t],
'b',
label=r'Wyestymowana krzywa wzorcowa')
plt.plot(t, [4 * D * i**expo for i in t],
'r',
label=r'Prawdziwa krzywa wzorcowa')
plt.xlabel('t')
plt.ylabel(r'$\rho(t)$')
plt.title('c', loc='left')
plt.gca().spines['top'].set_visible(False)
plt.gca().spines['right'].set_visible(False)
plt.savefig(path + '/TAMSD.pdf',
transparent=True,
bbox_inches='tight',
dpi=300)
plt.cla()
plt.loglog(t, tamsds, '.', label='punkty TAMSD')
plt.loglog(t, [4 * D * i**expo_est for i in t],
'b',
label=r'Wyestymowana krzywa TAMSD')
plt.loglog(t, [4 * D * i**expo for i in t],
'r',
label=r'Prawdziwa krzywa wzorcowa')
plt.xlabel('t')
plt.ylabel(r'$\rho(t)$')
plt.legend(loc='lower left', bbox_to_anchor=(1.05, 1))
plt.title('d', loc='left')
plt.gca().spines['top'].set_visible(False)
plt.gca().spines['right'].set_visible(False)
plt.savefig(path + '/TAMSD_loglog.pdf',
transparent=True,
bbox_inches='tight',
dpi=300)
# perfekcyjne tamsd
plt.cla()
D = 0.3
t = [0.1 * i for i in range(101)]
exps = [0.7, 1, 1.3]
label = ['superdyfuzja', 'dyfuzja normalna', 'subdyfuzja']
for expo in exps:
plt.plot(t, [4 * D * i**expo for i in t],
color=colors[exps.index(expo)],
label=r'$\alpha=\ $' + str(expo) + ' - ' +
label[-exps.index(expo) - 1])
plt.xlabel('t')
plt.ylabel(r'$\rho(t)$')
plt.legend(loc='lower left', bbox_to_anchor=(1.05, 1), ncol=3)
plt.title('a', loc='left')
plt.gca().spines['top'].set_visible(False)
plt.gca().spines['right'].set_visible(False)
plt.savefig(path + '/perfect_TAMSD.pdf',
transparent=True,
bbox_inches='tight',
dpi=300)
# perfekcyjne tamsd - loglog
plt.cla()
D = 1
t = [0.1 * i for i in range(101)]
exps = [0.7, 1, 1.3]
for expo in exps:
plt.loglog(t, [4 * D * i**expo for i in t],
color=colors[exps.index(expo)],
label=r'$\alpha=\ $' + str(expo))
plt.xlabel('t')
plt.ylabel(r'$\rho(t)$')
plt.title('b', loc='left')
plt.gca().spines['top'].set_visible(False)
plt.gca().spines['right'].set_visible(False)
plt.savefig(path + '/perfect_TAMSD_loglog.pdf',
transparent=True,
bbox_inches='tight',
dpi=300)
logg('Generowanie przykładowych TAMSD - stop')
print(' --- ZAKOŃCZONO')