def numb_trees(class_, method, y_train, y_test):
trees = range(1, 50)
#trees = [1,3,5, 10, 15, 20, 50, 100, 150]
#trees = np.linspace(1,n,n)
train_accuracy = []
val_accuracy = []
train_auc = []
val_auc = []
for i in trees:
if method == 'random_forest':
y_pred_train, y_pred_val = class_.random_forest(n_estimators=i)[:2]
xlabel = 'Number of trees'
title = 'Random forest - number of trees'
name_fig = 'RF_numbTrees'
anal = Analyse(y_train, y_test, y_pred_train, y_pred_val)
accuracy_train, accuracy_val = anal.accuracy()
auc_train, auc_val = anal.roc()[4:]
train_accuracy.append(accuracy_train)
val_accuracy.append(accuracy_val)
train_auc.append(auc_train)
val_auc.append(auc_val)
#all_accuracies = cross_val_score(estimator=class_.gradient_boosting(n_estimators=i))
make_plot(trees, train_accuracy, val_accuracy, train_auc, val_auc, xlabel,
title, name_fig)
def tree_depth(class_, method, y_train, y_test):
depth = range(1, 30)
#depth = [2,3,5,7,10,13,15,18, 20,30]
train_accuracy = []
val_accuracy = []
train_auc = []
val_auc = []
for i in depth:
if method == 'random_forest':
y_pred_train, y_pred_val = class_.random_forest(max_depth=i)[:2]
xlabel = 'max depth'
title = 'Random forest - tree depth'
name_fig = 'RF_TreeDepth'
if method == 'decision_tree':
y_pred_train, y_pred_val = class_.decision_tree(max_depth=i)[:2]
xlabel = 'max depth'
title = 'Decision tree - tree depth'
name_fig = 'DT_TreeDepth'
anal = Analyse(y_train, y_test, y_pred_train, y_pred_val)
accuracy_train, accuracy_val = anal.accuracy()
auc_train, auc_val = anal.roc()[4:]
train_accuracy.append(accuracy_train)
val_accuracy.append(accuracy_val)
train_auc.append(auc_train)
val_auc.append(auc_val)
make_plot(depth, train_accuracy, val_accuracy, train_auc, val_auc, xlabel,
title, name_fig)
def max_iterations(class_, method, y_train, y_test, max_it):
iterations = np.linspace(1, max_it, dtype=int)
train_accuracy = []
val_accuracy = []
train_auc = []
val_auc = []
for i in iterations:
if method == 'neural_network':
y_pred_train, y_pred_val = class_.neural_network(max_iter=i)[:2]
xlabel = 'max iterations'
title = 'Neural network - max iterations'
name_fig = 'NN_max_iterations'
elif method == 'logistic_regression':
y_pred_train, y_pred_val = class_.logistic_regression(
max_iter=i)[:2]
xlabel = 'max iterations'
title = 'Logistic regression- max iterations'
name_fig = 'LR_max_iterations'
anal = Analyse(y_train, y_test, y_pred_train, y_pred_val)
accuracy_train, accuracy_val = anal.accuracy()
auc_train, auc_val = anal.roc()[4:]
train_accuracy.append(accuracy_train)
val_accuracy.append(accuracy_val)
train_auc.append(auc_train)
val_auc.append(auc_val)
make_plot(iterations, train_accuracy, val_accuracy, train_auc, val_auc,
xlabel, title, name_fig)
def main():
block_db, resource_db = get_dbs(r'D:\Program Files\SteamLibrary')
blocks, resources = unpack_dbs(block_db['data'], resource_db['data'])
trim(blocks)
print()
Analyse(blocks, resources).analyse()
def get_bar_graph_data(self, data):
"""
Returns the bar graph data for a particular user
:param data: Dictionary, schema: {'user_id' : ${user_id}}
"""
sql = """
select l.user_id, t.task, l.tstamp
from %s l
join %s t
on l.task_id = t.task_id
where l.user_id = %s
order by l.tstamp asc
""" % (self.work_tracker_log._name, self.tasks._name, '%(user_id)s')
self.db._cur.execute(sql, data)
cols = [desc[0] for desc in self.db._cur.description]
data = self.db._cur.fetchall()
self.db.commit()
log_data = [dict(zip(cols, row)) for row in data]
if log_data == []:
return log_data
bar_data = Analyse(log_data).get_bar_grouping_dict()
for row in bar_data:
row['x'] = row['task']
row['y'] = row['time_spent']
del row['task']
del row['time_spent']
return bar_data
def min_samples_leaf(class_, method, y_train, y_test):
samples_leaf = [0.1, 0.25, 0.5, 1, 2, 3]
#samples_leaf = np.linspace(0.1,0.05*n,n)
train_accuracy = []
val_accuracy = []
train_auc = []
val_auc = []
for i in samples_leaf:
if method == 'decision_tree':
y_pred_train, y_pred_val = class_.random_forest(
min_samples_leaf=i)[:2]
xlabel = 'min samples leaf'
title = 'Decision tree - min samples leaf'
name_fig = 'DT_min_samples_leaf'
if method == 'random_forest':
y_pred_train, y_pred_val = class_.random_forest(
min_samples_leaf=i)[:2]
xlabel = 'min samples leaf'
title = 'Random forest - min samples leaf'
name_fig = 'RF_min_samples_leaf'
anal = Analyse(y_train, y_test, y_pred_train, y_pred_val)
accuracy_train, accuracy_val = anal.accuracy()
auc_train, auc_val = anal.roc()[4:]
train_accuracy.append(accuracy_train)
val_accuracy.append(accuracy_val)
train_auc.append(auc_train)
val_auc.append(auc_val)
make_plot(samples_leaf, train_accuracy, val_accuracy, train_auc, val_auc,
xlabel, title, name_fig)
def analyse(args):
analise_results = Analyse(args.original_swarm_file,
args.corrected_swarm_file,
args.failed_swarm_file, args.analyse_file,
args.analyse_file_mode, args.dense_layers,
args.threshold, args.pif, args.dataset,
args.seed)
analise_results.run_analise()
analise_results.write_results_analyse()
def run(self):
args = copy.deepcopy(vars(self))
jobs = []
if self.run_type == "merge":
Analyse(args)
elif self.run_type == "preprocess":
for run in self.runs:
print("Starting script for run {}\n".format(run))
args["asic"] = 0
args["runs"] = [run]
p = multiprocessing.Process(target=Analyse, args=(args,))
jobs.append(p)
p.start()
for job in jobs:
job.join()
else:
args_ch = copy.deepcopy(args)
for m in self.module:
for asic in self.asic_list:
print("Starting script for module {} and asic {}\n"
.format(m, asic))
args["module"] = m
args["channel"] = None
args["asic"] = asic
p = multiprocessing.Process(target=Analyse, args=(args,))
jobs.append(p)
p.start()
for ch in self.channel:
for asic in self.asic_list:
print("Starting script for channel {} and asic {}\n"
.format(ch, asic))
args_ch["module"] = None
args_ch["channel"] = ch
args_ch["asic"] = asic
p = multiprocessing.Process(target=Analyse, args=(args_ch,))
jobs.append(p)
p.start()
for job in jobs:
job.join()
def __send(self):
self.__setTime()
account_sid = 'AC7c4003f4b37c35d2e4249984df784b69'
auth_token = '6345546fae4ad92e602570250760c0fe'
client = Client(account_sid, auth_token)
message = client.messages.create(body=self.__getInfo()[0],
from_='(239) 237-3586',
to=self.__phone_number)
info = SetData(self.__getInfo()[1], self.__getInfo()[2])
print(self.__getInfo()[0])
info.write()
x = Analyse('/Python/Code/data.xls')
x.createPic()
time.sleep(23 * 60 * 60)
def learning_rate(class_, method, y_train, y_test):
rates = [0.0001, 0.001, 0.01, 0.1, 1.0]
train_accuracy = []
val_accuracy = []
train_auc = []
val_auc = []
for i in rates:
y_pred_train, y_pred_val = class_.gradient_boosting(learning_rate=i)
anal = Analyse(y_train, y_test, y_pred_train, y_pred_val)
accuracy_train, accuracy_val = anal.accuracy()
auc_train, auc_val = anal.roc()[4:]
train_accuracy.append(accuracy_train)
val_accuracy.append(accuracy_val)
train_auc.append(auc_train)
val_auc.append(auc_val)
xlabel = 'Learning rate'
title = 'Gradient boosting - learning rate'
name_fig = 'GB_learningrate'
make_plot(rates, train_accuracy, val_accuracy, train_auc, val_auc, xlabel,
title, name_fig)
def hidden_layers(class_, y_train, y_test):
layers = [1, 4, 10, 20, 50, 100, 200, 250]
train_accuracy = []
val_accuracy = []
train_auc = []
val_auc = []
for i in layers:
y_pred_train, y_pred_val = class_.neural_network(
hidden_layer_sizes=i)[:2]
anal = Analyse(y_train, y_test, y_pred_train, y_pred_val)
accuracy_train, accuracy_val = anal.accuracy()
auc_train, auc_val = anal.roc()[4:]
train_accuracy.append(accuracy_train)
val_accuracy.append(accuracy_val)
train_auc.append(auc_train)
val_auc.append(auc_val)
xlabel = 'hidden layers'
title = 'Neural network - hidden layers'
name_fig = 'NN_hiddenlayers'
make_plot(layers, train_accuracy, val_accuracy, train_auc, val_auc, xlabel,
title, name_fig)
def min_samples_split(class_, method, y_train, y_test):
samples_split = [0.1, 0.5, 2, 4, 6]
#samples_leaf = np.linspace(0.1,0.05*n,n)
train_accuracy = []
val_accuracy = []
train_auc = []
val_auc = []
for i in samples_split:
if method == 'decision_tree':
y_pred_train, y_pred_val = class_.random_forest(
min_samples_split=i)[:2]
xlabel = 'min samples split'
title = 'Decision tree - min samples spit'
name_fig = 'DT_min_samples_split'
if method == 'random_forest':
y_pred_train, y_pred_val = class_.random_forest(
min_samples_split=i)[:2]
xlabel = 'min samples split'
title = 'Random forest - min samples split'
name_fig = 'RF_min_samples_split'
if method == 'adaboost':
y_pred_train, y_pred_val = class_.adaboost(min_samples_split=i)[:2]
xlabel = 'min samples split'
title = 'Gradient boosting - min samples split'
name_fig = 'GB_min_samples_split'
anal = Analyse(y_train, y_test, y_pred_train, y_pred_val)
accuracy_train, accuracy_val = anal.accuracy()
auc_train, auc_val = anal.roc()[4:]
train_accuracy.append(accuracy_train)
val_accuracy.append(accuracy_val)
train_auc.append(auc_train)
val_auc.append(auc_val)
make_plot(samples_split, train_accuracy, val_accuracy, train_auc, val_auc,
xlabel, title, name_fig)
def get_line_graph_data(self, data):
"""
Returns the line graph data for a particular user
:param data: Dictionary, schema: {'user_id' : ${user_id}}
"""
sql = """
select l.user_id, t.task, l.tstamp
from %s l
join %s t
on l.task_id = t.task_id
where l.user_id = %s
order by l.tstamp asc
""" % (self.work_tracker_log._name, self.tasks._name, '%(user_id)s')
self.db._cur.execute(sql, data)
cols = [desc[0] for desc in self.db._cur.description]
data = self.db._cur.fetchall()
self.db.commit()
log_data = [dict(zip(cols, row)) for row in data]
if log_data == []:
return [[]]
line_data = Analyse(log_data).get_line_grouping_dict()
# We have to slightly restructure it for use with react-easy-chart
transformed = collections.defaultdict(list)
for row in line_data:
transformed[row['task']].append({
'x': row['time'].split('.')[0],
'y': row['total_time_spent']
})
transformed = [v for k, v in transformed.items()]
# Trim dates
return transformed
print(f'NEW: {self.base_heatmap}')
ax = sns.heatmap(self.base_heatmap)
plt.show()
class BarGraph:
def __init__(self, data):
self.data = data
def draw_bar_graph(self):
x_ref = list(self.data.keys())
y_ref = list(self.data.values())
x_pos = [i for i, _ in enumerate(x_ref)]
plt.bar(x_pos, y_ref, color='green')
plt.xlabel('Stagnation period (s)')
plt.ylabel('Frequency')
plt.xticks(x_pos, x_ref)
plt.show()
mouse_heatmap = HeatMap("./track4.csv")
mouse_heatmap.create_base_heatmap()
mouse_heatmap.fill_heatmap()
analysis = Analyse("./track4.csv")
analysis.get_file_content()
mouse_bar_chart = BarGraph(analysis.get_mouse_movement_duration_by_frequency())
mouse_bar_chart.draw_bar_graph()
def setUpClass(cls):
# Construct our original data set
cls.data = [{
'user_id':
'test user',
'task':
'1',
'tstamp':
datetime.datetime(2018, 7, 26, 20, 00, 00, 000000)
}, {
'user_id':
'test user',
'task':
'2',
'tstamp':
datetime.datetime(2018, 7, 26, 20, 10, 00, 000000)
}, {
'user_id':
'test user',
'task':
'1',
'tstamp':
datetime.datetime(2018, 7, 26, 20, 15, 00, 000000)
}, {
'user_id':
'test user',
'task':
'2',
'tstamp':
datetime.datetime(2018, 7, 26, 20, 20, 00, 000000)
}, {
'user_id':
'test user',
'task':
'1',
'tstamp':
datetime.datetime(2018, 7, 26, 20, 40, 00, 000000)
}]
# Initalise our instance of Analyse
cls.analyse = Analyse(cls.data)
# Construct some DataFrames to use later in our unit test package
# For comparing analyse.df_raw
cls.raw_df = DataFrame(cls.data)
# For comparing analyse.df_transform
cls.transform_df = DataFrame([{
'task':
'1',
'started':
datetime.datetime(2018, 7, 26, 20, 00, 00, 000000),
'finished':
datetime.datetime(2018, 7, 26, 20, 10, 00, 000000),
'time_spent':
600.00
}, {
'task':
'2',
'started':
datetime.datetime(2018, 7, 26, 20, 10, 00, 000000),
'finished':
datetime.datetime(2018, 7, 26, 20, 15, 00, 000000),
'time_spent':
300.00
}, {
'task':
'1',
'started':
datetime.datetime(2018, 7, 26, 20, 15, 00, 000000),
'finished':
datetime.datetime(2018, 7, 26, 20, 20, 00, 000000),
'time_spent':
300.00
}, {
'task':
'2',
'started':
datetime.datetime(2018, 7, 26, 20, 20, 00, 000000),
'finished':
datetime.datetime(2018, 7, 26, 20, 40, 00, 000000),
'time_spent':
1200.00
}])
cls.transform_df = cls.transform_df[[
'task', 'started', 'finished', 'time_spent'
]]
# For comparing analyse.df_bar
cls.bar_df = DataFrame([{
'task': '1',
'time_spent': 900.00
}, {
'task': '2',
'time_spent': 1500.00
}])
cls.bar_df = cls.bar_df[['task', 'time_spent']]
# For comparing analyse.df_line
cls.line_df = DataFrame([
{
'task': '1',
'time': datetime.datetime(2018, 7, 26, 20, 00, 00, 000000),
'total_time_spent': 0.00
},
{
'task': '2',
'time': datetime.datetime(2018, 7, 26, 20, 10, 00, 000000),
'total_time_spent': 0.00
},
{
'task': '1',
'time': datetime.datetime(2018, 7, 26, 20, 15, 00, 000000),
'total_time_spent': 600.00
},
{
'task': '2',
'time': datetime.datetime(2018, 7, 26, 20, 20, 00, 000000),
'total_time_spent': 300.00
},
{
'task': '1',
'time': datetime.datetime(2018, 7, 26, 20, 10, 00, 000000),
'total_time_spent': 600.00
},
{
'task': '2',
'time': datetime.datetime(2018, 7, 26, 20, 15, 00, 000000),
'total_time_spent': 300.00
},
{
'task': '1',
'time': datetime.datetime(2018, 7, 26, 20, 20, 00, 000000),
'total_time_spent': 900.00
},
{
'task': '2',
'time': datetime.datetime(2018, 7, 26, 20, 40, 00, 000000),
'total_time_spent': 1500.00
},
])
cls.line_df = cls.line_df[['task', 'time', 'total_time_spent']]
import os
import sys
from keylogger import Keylogger
from analyse import Analyse
def using():
print("Usage: python App.py {start|analys}\n")
print("start - start keylogger, all symbols will write in file(~/pylogger.log or $pylogger_file)")
print("analys - start analyse ~/pylogger and do plot and save it in ./analyse.png")
sys.exit(2)
if len(sys.argv) < 2:
using()
command = sys.argv[1]
if command == "start":
Keylogger().start()
elif command == "analyse":
analyse = Analyse()
analyse.do_and_save_plot()
else:
using()
def qlearning(self, eps): #The Q-learning algorithm to train our agent
self.set_velocity_mode(self.myControlledCarId, 0)
reward_type = "security_distance"
speedLimit = True
state = None
steps = 0
plottingList = {
"collisions": [],
"space_headway": [],
"relative_speed": [],
"speed": [],
"steps": 0
}
while True:
print(state)
if state:
plottingList["space_headway"].append(
state.get("space_headway"))
plottingList["relative_speed"].append(
round(state.get("relative_speed") * 3.6,
0)) #Metre par seconde from traci to km par seconde
plottingList["speed"].append(round(
state.get("speed") * 3.6,
0)) #Metre par seconde from traci to km par seconde
d_t, ds_t, s_t = \
self.arrange(state.get('space_headway'), self.index_space_headway), \
self.arrange(state.get('relative_speed'), self.index_relative_speed), \
self.arrange(state.get('speed'), self.index_speed)
a = self.Egreedy_policy(d_t, ds_t, s_t)
q_t = self.q[self.index_space_headway.get(d_t),
self.index_relative_speed.get(ds_t),
self.index_speed.get(s_t),
self.index_action.get(self.action[a])]
#Get the updated speed
update_speed = self.update_speed(self.action[a],
state.get('speed'))
#Update agent speed ,step from traci
self.set_velocity(self.myControlledCarId, update_speed)
#Simulate new step with traci
self.generate_simulation_step()
next_state = self.get_state(self.myControlledCarId)
q_t_m = None
#Check if our agent has been collided with an other vehicle
if self.isCollided(self.myControlledCarId):
#Affect reward -10
self.set_reward_after_collision(
reward_type) #reward_type "collision"
#Set agent speed to 0
self.set_velocity(self.myControlledCarId, 0)
q_t_m = 0
state = None
plottingList["collisions"].append(steps)
elif next_state:
if reward_type == "security_distance":
self.set_reward_security_dist_volicity(
next_state.get('space_headway'),
next_state.get('speed'), speedLimit)
print(f" total reward : {self.totalRewards}")
d_t1, ds_t1, s_t1 = \
self.arrange(next_state.get('space_headway'), self.index_space_headway), \
self.arrange(next_state.get('relative_speed'), self.index_relative_speed), \
self.arrange(next_state.get('speed'), self.index_speed)
q_t_m = np.max(self.q[self.index_space_headway.get(d_t1),
self.index_relative_speed.get(ds_t1),
self.index_speed.get(s_t1)])
state = next_state
if q_t_m is not None:
self.q[
self.index_space_headway.get(d_t),
self.index_relative_speed.get(ds_t),
self.index_speed.get(s_t),
self.index_action.get(self.action[a])] = \
(1 - self.alpha) * q_t + self.alpha * (self.totalRewards + self.gamma * q_t_m)
print(
f"qlearning: {self.q[self.index_space_headway.get(d_t), self.index_relative_speed.get(ds_t), self.index_speed.get(s_t)]}"
)
steps += 1
self.epsilon_period(steps)
else:
self.generate_simulation_step()
state = self.get_state(self.myControlledCarId)
self.set_velocity(self.myControlledCarId, 0)
if steps > (eps * 10000):
time.sleep(.1)
if steps == eps * 10000:
plottingList["steps"] = steps
plotting = Analyse(self, plottingList)
plotting.plot_all_result()
def main():
parser = _build_args_parser()
args = parser.parse_args()
# -------------------Gestion des données--------------------------
print("\n" + "Gestion des données...")
bd = BaseDonnees(args.fichier, 'is_legendary')
bd.voir_att()
bd.enlever_attributs([
'abilities', 'japanese_name', 'name', 'generation', 'pokedex_number',
'classfication'
])
bd.str_a_int(['capture_rate'])
bd.str_a_vec(['type1', 'type2'])
bd.normaliser_donnees()
bd.methode_filtrage()
if (bool(args.est_ech_poids)):
poids = bd.definir_poids_att()
else:
poids = []
# -------------------Gestion du modèle----------------------------
print("\n" + "Création du modèle...")
if (args.choix_modele == "bayes_naif"):
modele = BayesNaif()
elif (args.choix_modele == "perceptron"):
modele = Perceptron(max_iter=args.max_iter_perceptron,
tol=args.tol_perceptron)
elif (args.choix_modele == "perceptron_mc"):
modele = PerceptronMC(couches_cachees=tuple(
[int(x) for x in args.couches_cachees.split(',')]),
activation=args.activation,
solutionneur=args.solutionneur,
max_iter=args.max_iter_perceptron_mc)
elif (args.choix_modele == "svm"):
modele = SVM(noyau=args.noyau,
tol=args.tol_svm,
max_iter=args.max_iter_svm)
elif (args.choix_modele == "fad"):
modele = FAD(nb_arbres=args.nb_arbres,
critere=args.critere,
prof_max=args.prof_max_fad)
elif (args.choix_modele == "adaboost"):
modele = AdaBoost(max_prof=args.prof_max_adaboost)
# -------------------Répétitions pour moyenner-----------
analyse_mult = Analyse_multiple(args.repetitions)
for rep in range(args.repetitions):
print("\n" + "Génération des ensembles d'entrainement et de test...")
x_entr, t_entr, x_test, t_test = bd.faire_ens_entr_test()
# -------------------Entrainement ou validation croisée-----------
if bool(args.vc) is False:
print("\n" + "Début de l'entrainement simple...")
modele.entrainement(x_entr, t_entr, args.est_ech_poids, poids)
else:
print("\n" + "Début de l'entrainement par validation croisée...")
modele.validation_croisee(x_entr, t_entr, 10, args.est_ech_poids,
poids)
# -------------------Prédiction et erreur-------------------------
print("\n" + "Calcul des erreurs...")
predictions_entrainement = modele.prediction(x_entr)
erreur_entrainement = modele.erreur(
t_entr, predictions_entrainement) / len(t_entr) * 100
predictions_test = modele.prediction(x_test)
erreur_test = modele.erreur(t_test,
predictions_test) / len(t_test) * 100
print("Erreur d'entrainement = ", erreur_entrainement, '%')
print("Erreur de test = ", erreur_test, '%')
# -------------------Analyse des résultats------------------------
print("\n" + "Analyse des résultats...")
prob = modele.confiance_test(x_test)
analyse = Analyse(t_test, predictions_test, prob)
analyse.calculer_comptes()
analyse.afficher_comptes()
analyse.calculer_metriques()
analyse.afficher_metriques()
if (bool(args.courbe_roc)):
analyse.calculer_courbe_roc()
analyse.afficher_courbe_roc()
analyse_mult.ajouter_erreurs(erreur_entrainement, erreur_test)
analyse_mult.ajouter_metriques(analyse.metriques)
analyse_mult.augmenter_rep_courante()
# -------------------Analyse des répétitions------------------------
if (args.repetitions > 1):
print("\n" + "Analyse des répétitions...")
analyse_mult.calculer_moyennes()
analyse_mult.afficher_moyennes()
analyse_mult.afficher_graphique()
DT_tuned = method.decision_tree(criterion='gini', max_depth=10, min_samples_leaf=2, min_samples_split=2, visualize_tree=False)
NN_tuned = method.neural_network(activation='tanh', max_iter=50, learning_rate=0.1, hidden_layer_sizes=(250,))
AB_tuned = method.adaboost(base_estimator=base_estimator[-1], n_estimators=200, learning_rate=0.1 )
return RF_tuned, AB_tuned, DT_tuned, NN_tuned
## Each method, with y_pred_train, y_pred_val, and method
#RF_tuned, AB_tuned, DT_tuned, NN_tuned = tuned_full_predictors()
RF_tuned, AB_tuned, DT_tuned, NN_tuned = tuned_dropped_predictors()
## Assigning analysis class to each classifier
anal_RF = Analyse(y_train, y_test, RF_tuned[0], RF_tuned[1])
anal_DT = Analyse(y_train, y_test, DT_tuned[0], DT_tuned[1])
anal_AB = Analyse(y_train, y_test, AB_tuned[0], AB_tuned[1])
anal_NN = Analyse(y_train, y_test, NN_tuned[0], NN_tuned[1])
## Getting the most important predictors for each method, as well as bar plot
DT = anal_DT.importance_predictors(DT_tuned[-1], feature_names, 'Feature importance - Decision tree', 'feature_importance_IP_DT')
RF = anal_RF.importance_predictors(RF_tuned[-1], feature_names, 'Feature importance - Random forest', 'feature_importance_IP_RT')
AB = anal_AB.importance_predictors(AB_tuned[-1], feature_names,'Feature importance - AnaBoost', 'feature_importance_IP_AB')
## Printing out accuracy and AUC
print("Accuracy scores:")
print("AdaBoost:", "train:", anal_AB.accuracy()[0], "val:", anal_AB.accuracy()[1])
print("Random forest:", "train:", anal_RF.accuracy()[0], "val:", anal_RF.accuracy()[1])
from datetime import datetime
from analyse import Analyse
logger = logging.getLogger()
logger.setLevel(logging.DEBUG)
ch = logging.StreamHandler()
ch.setLevel(logging.DEBUG)
formatter = logging.Formatter('[%(asctime)s][%(levelname)s] %(message)s')
ch.setFormatter(formatter)
logger.addHandler(ch)
user_name = sys.argv[1]
user_pwd = sys.argv[2]
url = sys.argv[3]
start = datetime.now()
a = Analyse(user_name, user_pwd, url)
end = datetime.now()
print('新增缺陷数：{}, 未关闭缺陷数：{}, 缺陷周期大于7天数：{}, 低级缺陷数：{}, 低级缺陷率: {}, '
'严重缺陷数: {}, 严重缺陷率：{}， 验证不通过缺陷数：{}'.format(a.get_bugs_new(),
a.get_bugs_open(),
a.get_bugs_more_than_7days(),
*a.get_bugs_small(),
*a.get_bugs_big(),
a.get_bugs_verified_nopass()))
print(end - start)