def get_density_plots(estimators_list,
simulators_dict,
path_to_results,
exp_prefix="question1_noise_reg_x",
task_ids=None):
"""
This function allows to compare plots from estimators and simulators (i.e. fitted and true densities). Two modes are currently available:
1) by specifying estimators and simulator, the function picks one result pair randomly that matches the given simulator/estimator
selection
2) by specifying the task_ids as list, it is possible to pick specific plots to compare
Args:
estimators: a list containing strings of estimators to be evaluated, e.g. ['KernelMixtureNetwork', 'MixtureDensityNetwork']
simulators: a dict containing specifications of a simulator under which the estimators shall be compared, e.g.
{'heteroscedastic': True, 'random_seed': 20, 'std': 1, 'simulator': 'EconDensity'}
path_to_results: absolute path to where the dumped model files are stored
exp_prefix: specifies the task question
Returns:
A list of figures for fitted and true densities.
"""
if task_ids is not None:
assert type(task_ids) == list
assert len(task_ids) == len(estimators_list)
RESULTS_FILE = 'results.pkl'
logger.configure(path_to_results, exp_prefix)
results_from_pkl_file = dict(logger.load_pkl_log(RESULTS_FILE))
gof_result = GoodnessOfFitResults(
single_results_dict=results_from_pkl_file)
results_df = gof_result.generate_results_dataframe(
base_experiment.KEYS_OF_INTEREST)
""" load model's estimators """
if task_ids is None:
models_of_interest = {
k: v
for k, v in gof_result.single_results_dict.items()
if v.probabilistic_model_params == simulators_dict and v.ndim_x +
v.ndim_y == 2
}
models = [
ConfigRunner.load_dumped_estimator(
take_of_type(1, estimator_str, models_of_interest))
for estimator_str in estimators_list
]
else:
models = [
ConfigRunner.load_dumped_estimators(gof_result, task_id=task_ids)
]
""" load model's simulators """
# todo: implement when simulator dumps exist
figs = []
for model in models:
graph = model.estimator.sess.graph
sess = tf.Session(graph=graph)
with sess:
sess.run(tf.global_variables_initializer())
model.estimator.sess = sess
""" fitted density figures"""
plt.suptitle(model.estimator.name)
fig_fitted = model.estimator.plot3d()
figs.append(fig_fitted)
""" true density figures """
# todo: use newly dumped simulators
sess.close()
return figs
'y_noise_std': [0.1],
},
}
simulators_params = {'LinearStudentT': {'ndim_x': [10]}}
observations = 100 * np.logspace(2, 6, num=8, base=2.0, dtype=np.int32)
return estimator_params, simulators_params, observations
if __name__ == '__main__':
estimator_params, simulators_params, observations = question4()
load = base_experiment.launch_experiment(estimator_params,
simulators_params,
observations,
EXP_PREFIX,
n_mc_samples=N_MC_SAMPLES,
tail_measures=False)
if load:
logger.configure(config.DATA_DIR, EXP_PREFIX)
results_from_pkl_file = dict(logger.load_pkl_log(RESULTS_FILE))
gof_result = GoodnessOfFitResults(
single_results_dict=results_from_pkl_file)
results_df = gof_result.generate_results_dataframe(
base_experiment.KEYS_OF_INTEREST)
gof_result = ConfigRunner.load_dumped_estimators(gof_result)
from cde.evaluation.simulation_eval import base_experiment
import cde.model_fitting.ConfigRunner as ConfigRunner
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
EXP_PREFIX = 'question2_entropy_reg'
RESULTS_FILE = 'results.pkl'
logger.configure(
'/home/jonasrothfuss/Dropbox/Eigene_Dateien/Uni/WS17_18/Density_Estimation/Nonparametric_Density_Estimation/data/cluster',
EXP_PREFIX)
results_from_pkl_file = dict(logger.load_pkl_log(RESULTS_FILE))
gof_result = GoodnessOfFitResults(single_results_dict=results_from_pkl_file)
results_df = gof_result.generate_results_dataframe(
base_experiment.KEYS_OF_INTEREST + ['entropy_reg_coef'])
#gof_result = ConfigRunner.load_dumped_estimators(gof_result, task_id=[5])
SMALL_SIZE = 11
MEDIUM_SIZE = 12
LARGE_SIZE = 16
TITLE_SIZE = 20
LINEWIDTH = 6
plt.rc('font', size=SMALL_SIZE) # controls default text sizes
plt.rc('axes', titlesize=LARGE_SIZE) # fontsize of the axes title
plt.rc('axes', labelsize=MEDIUM_SIZE) # fontsize of the x and y labels
plt.rc('xtick', labelsize=SMALL_SIZE) # fontsize of the tick labels
plt.rc('ytick', labelsize=SMALL_SIZE) # fontsize of the tick labels
## SKEW Normal
EXP_PREFIX = 'question4_benchmark_skew_NF'
RESULTS_FILE = 'results.pkl'
if not os.path.isdir(EXP_PREFIX):
os.makedirs(EXP_PREFIX)
logger.configure(
'/home/simon/Documents/KIT/Informatik/Bachelorarbeit/Conditional_Density_Estimation/data/cluster',
EXP_PREFIX)
results_from_pkl_file = dict(logger.load_pkl_log(RESULTS_FILE))
gof_result = GoodnessOfFitResults(single_results_dict=results_from_pkl_file)
results_df = gof_result.generate_results_dataframe(base_experiment.KEYS_OF_INTEREST + ['bandwidth'])
plot_dict = dict([(simulator,
{"MDN": {"simulator": simulator, "estimator": "MixtureDensityNetwork", "x_noise_std": 0.1},
"KMN": {"simulator": simulator, "estimator": "KernelMixtureNetwork", "x_noise_std": 0.1},
"LSCDE": {"simulator": simulator, "estimator": "LSConditionalDensityEstimation"},
"CKDE": {"simulator": simulator, "estimator": "ConditionalKernelDensityEstimation", "bandwidth": "normal_reference"},
"CKDE_CV": {"simulator": simulator, "estimator": "ConditionalKernelDensityEstimation", "bandwidth": "cv_ml"},
"NKDE": {"simulator": simulator, "estimator": "NeighborKernelDensityEstimation"},
"NF": {"simulator": simulator, "estimator": "NormalizingFlowEstimator",}
}) for simulator in ["EconDensity", "ArmaJump", "SkewNormal"]])
fig = gof_result.plot_metric(plot_dict, metric="hellinger_distance", figsize=(15, 5.5))
## ARMA JUMP
EXP_PREFIX = "question8_benchmark"
RESULTS_FILE = "results.pkl"
CLUSTER_DIR = "/local/rojonas/cde/data/local"
LOCATION = "{}/{}/{}".format(CLUSTER_DIR, EXP_PREFIX, RESULTS_FILE)
DATA_DIR_LOCAL = "/home/jonasrothfuss/Dropbox/Eigene_Dateien/ETH/02_Projects/02_Noise_Regularization/02_Code_Conditional_Density_Estimation/data/cluster"
logger.configure(
#"/local/rojonas/cde/data/local",
DATA_DIR_LOCAL,
#CLUSTER_DIR,
EXP_PREFIX,
)
results_from_pkl_file = dict(logger.load_pkl_log(RESULTS_FILE))
gof_result = GoodnessOfFitResults(single_results_dict=results_from_pkl_file)
results_df = gof_result.generate_results_dataframe(base_experiment.KEYS_OF_INTEREST_LOGPROB + ["bandwidth", "param_selection"])
results_df.replace(to_replace=[None], value="None", inplace=True)
# seprarate 2d and 4d GMM
results_df.index = list(range(len(results_df)))
for i, row in results_df[['simulator', 'ndim_y']].iterrows():
if row['simulator'] == 'GaussianMixture':
results_df.at[i, 'simulator'] = '%s_%id'%(row['simulator'], row['ndim_y'])
estimators = [
"MixtureDensityNetwork",
"KernelMixtureNetwork",
"NormalizingFlowEstimator",
"ConditionalKernelDensityEstimation",
"NeighborKernelDensityEstimation",