cols = [
'Tectonic regime', 'Period', 'Lithology', 'Structural setting', 'Gross',
'Netpay', 'Porosity', 'Permeability', 'Depth'
]
h = h[cols]
p2 = time.time()
print(f"Time elapsed for uploading data: {p2 - p1}")
encoder = pp.LabelEncoder()
discretizer = pp.KBinsDiscretizer(n_bins=5,
encode='ordinal',
strategy='uniform')
p = Preprocessor([('encoder', encoder)])
discretized_data, est = p.apply(h)
info = p.info
# --------------------- VALIDATION TEST-------------------------------
nodes_type_mixed = gru.nodes_types(h)
columns = [
col for col in h.columns.to_list()
if nodes_type_mixed[col] in ['disc', 'disc_num']
] # GET ONLY DISCRETE
discrete_data = h[columns]
discretized_data, est = p.apply(discrete_data) # warning
info = p.info
bn = Networks.HybridBN()
from bamt.Preprocessors import Preprocessor
import pandas as pd
from sklearn import preprocessing as pp
import bamt.Networks as Networks
vk_data = pd.read_csv(r"data\real data\vk_data.csv").sample(150)
encoder = pp.LabelEncoder()
discretizer = pp.KBinsDiscretizer(n_bins=5,
encode='ordinal',
strategy='uniform')
p = Preprocessor([('encoder', encoder)])
discretized_data, est = p.apply(vk_data)
info = p.info
bn = Networks.HybridBN(has_logit=False, use_mixture=False)
bn.add_nodes(descriptor=info)
params = {
"init_nodes": ["sex", "has_pets", "is_parent", "relation", "tr_per_month"],
"init_edges": [("age", "mean_tr"), ("sex", "mean_tr"), ("sex", "has_pets"),
("is_parent", "has_pets"), ("has_pets", "median_tr"),
("is_driver", "tr_per_month"),
("tr_per_month", "median_tr"), ("tr_per_month", "relation")]
}
bn.add_edges(data=discretized_data,
optimizer='HC',
scoring_function=('MI', ),
params=params)
bn.fit_parameters(data=vk_data)
'Tectonic regime', 'Period', 'Lithology', 'Structural setting', 'Gross',
'Netpay', 'Porosity', 'Permeability', 'Depth'
]].dropna()
cont_test_data = cont_data[cont_data.columns[:-1]]
cont_target = cont_data[cont_data.columns[-1]]
disc_test_data = disc_data[disc_data.columns[:-1]]
disc_target = disc_data[disc_data.columns[-1]]
hybrid_test_data = hybrid_data[hybrid_data.columns[:-1]]
hybrid_target = hybrid_data[hybrid_data.columns[-1]]
encoder = pp.LabelEncoder()
discretizer = pp.KBinsDiscretizer(n_bins=5,
encode='ordinal',
strategy='uniform')
p = Preprocessor([('encoder', encoder), ('discretizer', discretizer)])
# Discrete pipeline
discretized_data, _ = p.apply(disc_data)
disc_bn = Networks.DiscreteBN()
info = p.info
disc_bn.add_nodes(info)
disc_bn.add_edges(data=discretized_data, scoring_function=('K2', K2Score))
disc_bn.fit_parameters(data=disc_data)
disc_bn.calculate_weights(discretized_data)
disc_predicted_values = disc_bn.predict(test=disc_test_data)
disc_predicted_values = pd.DataFrame.from_dict(disc_predicted_values,
orient='columns')
synth_disc_data = disc_bn.sample(50)
disc_bn.save('./disc_bn.json')
print(f"Time elapsed for importing: {p1 - start}")
h = pd.read_csv("data/real data/hack_processed_with_rf.csv")
cols = ['Tectonic regime', 'Period', 'Lithology', 'Structural setting', 'Gross', 'Netpay', 'Porosity', 'Permeability',
'Depth']
h = h[cols]
print(h.describe())
print("-----")
p2 = time.time()
print(f"Time elapsed for preparing data: {p2 - p1}")
encoder = pp.LabelEncoder()
discretizer = pp.KBinsDiscretizer(n_bins=5, encode='ordinal', strategy='quantile')
p = Preprocessor([('encoder', encoder), ('discretizer', discretizer)])
# -----------
discrete_data, est = p.apply(h)
info = p.info
bn = Networks.HybridBN(has_logit=True) # all may vary
bn.add_nodes(descriptor=info)
bn.add_edges(data=discrete_data, optimizer='HC', scoring_function=('MI',))
bn.get_info(as_df=False)
t1 = time.time()
bn.fit_parameters(data=h)
t2 = time.time()
print(f'PL elapsed: {t2 - t1}')
from bamt.Preprocessors import Preprocessor
import pandas as pd
from sklearn import preprocessing as pp
vk_data = pd.read_csv("data/real data/vk_data.csv")
encoder = pp.LabelEncoder()
discretizer = pp.KBinsDiscretizer(n_bins=5, encode='ordinal', strategy='uniform')
p = Preprocessor([('encoder', encoder), ('discretizer', discretizer)])
data, en = p.apply(vk_data)
# for i, j in en.items():
# print(f"{i}:{j}")
# ------------------------
p2 = Preprocessor([('discretizer', discretizer)])
data, en = p2.apply(vk_data)
print(data)
p1 = time.time()
print(f"Time elapsed for importing: {p1 - start}")
h = pd.read_csv("data/real data/hack_processed_with_rf.csv")
cols = ['Tectonic regime', 'Period', 'Lithology', 'Structural setting', 'Gross', 'Netpay', 'Porosity', 'Permeability',
'Depth']
h = h[cols]
print(h.describe())
p2 = time.time()
print(f"Time elapsed for uploading data: {p2 - p1}")
discretizer = pp.KBinsDiscretizer(n_bins=5, encode='ordinal', strategy='quantile')
p = Preprocessor([('discretizer', discretizer)])
# -----------
nodes_type_mixed = p.get_nodes_types(h)
columns = [col for col in h.columns.to_list() if not nodes_type_mixed[col] in ['disc', 'disc_num']] # GET ONLY CONT
discrete_data = h[columns]
discretized_data, est = p.apply(discrete_data) # info
info = p.info
bn = Networks.ContinuousBN(use_mixture=True) # use_mixture = False as well
bn.add_nodes(descriptor=info)
bn.add_edges(data=discretized_data, optimizer='HC', scoring_function=('MI',))
bn.get_info(as_df=False)
p1 = time.time()
print(f"Time elapsed for importing: {p1 - start}")
vk_data = pd.read_csv(r"data/real data/vk_data.csv")
ROWS = 50
vk_data = vk_data.iloc[:ROWS, :]
p2 = time.time()
print(f"Time elapsed for uploading data: {p2 - p1}")
encoder = pp.LabelEncoder()
discretizer = pp.KBinsDiscretizer(n_bins=5,
encode='ordinal',
strategy='uniform')
p = Preprocessor([('encoder', encoder), ('discretizer', discretizer)])
discretized_data, est = p.apply(vk_data)
info = p.info
bn = Networks.DiscreteBN()
bn.add_nodes(descriptor=info) # error
params = {'init_nodes': None, 'bl_add': None}
bn.add_edges(data=discretized_data,
optimizer='HC',
scoring_function=('K2', K2Score),
params=params) # error
# # --------------------
