def test_model_fitting(self):
df = pd.read_csv(
"C:/code/python/interpretable_decision_sets/data/titanic.csv")
cars = mine_CARs(df, rule_cutoff=40)
quant_df = QuantitativeDataFrame(df)
ids = IDS()
ids.fit(quant_df, cars, debug=False)
auc = ids.score_auc(quant_df)
def test_optimization(self):
df = pd.read_csv("C:/code/python/interpretable_decision_sets/data/titanic.csv")
ids_ruleset = mine_IDS_ruleset(df, rule_cutoff=40)
quant_df = QuantitativeDataFrame(df)
ascent = CoordinateAscentOptimizer(IDS(), maximum_consecutive_iterations=1)
lambdas = ascent.fit(ids_ruleset, quant_df, quant_df)
def test_random_seed(self):
replications_n = 10
cars_to_mine = 10
df = pd.read_csv("data/iris0.csv")
quant_df = QuantitativeDataFrame(df)
mined_cars_mupliple = []
mined_cars_comparison_results = []
for _ in range(replications_n):
ClassAssocationRule.id = 0
cars = mine_CARs(df, cars_to_mine)
mined_cars_mupliple.append(cars)
for idx in range(replications_n):
same = _all_rules_same(mined_cars_mupliple[0],
mined_cars_mupliple[idx])
mined_cars_comparison_results.append(same)
self.assertTrue(np.all(mined_cars_comparison_results))
ids_models_multiple = []
ids_comparison_results = []
for _ in range(replications_n):
ids = IDS()
ids = ids.fit(quant_dataframe=quant_df,
class_association_rules=cars,
debug=False,
random_seed=2)
ids_models_multiple.append(ids.clf.rules)
for idx in range(replications_n):
same = _all_rules_same(ids_models_multiple[0],
ids_models_multiple[idx])
ids_comparison_results.append(same)
self.assertTrue(np.all(ids_comparison_results))
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import random
from sklearn.metrics import accuracy_score, auc, roc_auc_score
from pyids.ids_rule import IDSRule
from pyids.ids_ruleset import IDSRuleSet
from pyids.ids_objective_function import ObjectiveFunctionParameters, IDSObjectiveFunction
from pyids.ids_optimizer import RSOptimizer, SLSOptimizer
from pyids.ids_cacher import IDSCacher
from pyids.ids_classifier import IDS, mine_CARs
from pyids.visualization import IDSVisualization
from pyarc.qcba import *
df = pd.read_csv("C:/code/python/interpretable_decision_sets/data/iris0.csv")
cars = mine_CARs(df, 20)
quant_df = QuantitativeDataFrame(df)
ids = IDS()
ids.fit(quant_df, cars, debug=False)
viz = IDSVisualization(ids, quant_df)
viz.visualize_dataframe()
# In[31]:
benchmark_data = []
for data_size in data_size_quantiles:
current_cars = cars[:RULE_COUNT_TO_USE]
current_df = df.sample(data_size)
current_quant_df = QuantitativeDataFrame(current_df)
times = []
for _ in range(PY_IDS_DURATION_ITERATIONS):
time1 = time.time()
lambda_array = [1.0] * 7 # use separate hyperparamter search routine
ids = IDS()
ids.fit(class_association_rules=current_cars,
quant_dataframe=current_quant_df,
debug=False)
time2 = time.time()
duration = time2 - time1
times.append(duration)
benchmark_data.append(dict(duration=np.mean(times), data_size=data_size))
# In[32]:
benchmark_dataframe_pyids = pd.DataFrame(benchmark_data)
from pyarc.qcba import *
from pyarc.algorithms import createCARs, top_rules
from pyarc import TransactionDB
from pyids.ids_classifier import IDS, mine_IDS_ruleset
from pyids.ids_cacher import IDSCacher
from pyids.ids_ruleset import IDSRuleSet
from pyids.ids_rule import IDSRule
from pyids.model_selection import encode_label, mode, RandomSearchOptimizer
df = pd.read_csv("./data/titanic.csv")
df["Died"] = df["Died"].astype(str) + "_"
ids_ruleset = mine_IDS_ruleset(df, 40)
quant_dataframe = QuantitativeDataFrame(df)
ids = IDS()
random_search = RandomSearchOptimizer(ids, debug=False, maximum_score_estimation_iterations=3, maximum_iterations=500)
result = random_search.fit(ids_ruleset, quant_dataframe, quant_dataframe)
print(result)
import pandas as pd
from collections import Counter
from pyarc.qcba.data_structures import QuantitativeDataFrame
from pyids.ids_classifier import IDS, mine_CARs
df = pd.read_csv("./data/titanic.csv")
cars = mine_CARs(df, 20)
quant_dataframe = QuantitativeDataFrame(df)
ids = IDS()
ids.fit(quant_dataframe, class_association_rules=cars, debug=False)
print(ids.score_auc(quant_dataframe, confidence_based=False))
print(ids.score_auc(quant_dataframe, confidence_based=True))
from pyids.ids_classifier import IDS, mine_IDS_ruleset
from pyids.ids_ruleset import IDSRuleSet
from pyids.model_selection import RandomSearchOptimizer, train_test_split_pd
from pyids.rule_mining import RuleMiner
df = pd.read_csv("../../data/titanic.csv")
rm = RuleMiner()
cars = rm.mine_rules(df, minsup=0.005)
ids_ruleset = IDSRuleSet.from_cba_rules(cars)
df_train, df_test = train_test_split_pd(df, prop=0.25)
quant_df_train, quant_df_test = QuantitativeDataFrame(df_train), QuantitativeDataFrame(df_test)
random_optimizer = RandomSearchOptimizer(IDS(), maximum_score_estimation_iterations=5, maximum_iterations=500)
lambda_array = random_optimizer.fit(ids_ruleset, quant_df_train, quant_df_test)
all_params = random_optimizer.score_params_dict
print(lambda_array)
with open("results/random_search_lambda_array.txt", "w") as file:
file.write(str(lambda_array))
with open("results/random_search_all_score_params.txt", "w") as file:
file.write(str(random_optimizer.score_params_dict))
df = pd.read_csv("../../data/titanic.csv")
cars = mine_CARs(df, rule_cutoff=40)
df_train, df_test = train_test_split_pd(df, prop=0.25)
quant_df_train, quant_df_test = QuantitativeDataFrame(
df_train), QuantitativeDataFrame(df_test)
lambda_array_coordinate_ascent = [18, 18, 18, 18, 18, 18, 18]
lambda_array_random_search = [
510.6938775510204, 694.1836734693878, 918.4489795918367,
286.42857142857144, 490.30612244897964, 694.1836734693878,
62.163265306122454
]
ids_ascent = IDS()
ids_random = IDS()
ids_basic = IDS()
ids_ascent.fit(quant_df_train,
cars,
debug=False,
lambda_array=lambda_array_coordinate_ascent)
ids_random.fit(quant_df_train,
cars,
debug=False,
lambda_array=lambda_array_random_search)
ids_basic.fit(quant_df_train, cars, debug=False, lambda_array=7 * [1])
ascent_metrics = calculate_ruleset_statistics(IDSRuleSet(ids_ascent.clf.rules),
quant_df_test)
import pandas as pd
from pyids.ids_classifier import IDS, mine_CARs
from pyarc.qcba.data_structures import QuantitativeDataFrame
df = pd.read_csv("./data/titanic.csv")
cars = mine_CARs(df, rule_cutoff=80)
quant_dataframe = QuantitativeDataFrame(df)
ids = IDS()
ids.fit(class_association_rules=cars, quant_dataframe=quant_dataframe, debug=True)
auc = ids.score_auc(quant_dataframe)
print(auc)
from pyids.rule_mining import RuleMiner
import pandas as pd
from pyids.ids_classifier import IDS
from pyarc.qcba.data_structures import QuantitativeDataFrame
from pyids.ids_ruleset import IDSRuleSet
rm = RuleMiner()
df = pd.read_csv("./data/titanic.csv")
cars = rm.mine_rules(df, minsup=0.001)
print(len(cars))
quant_df = QuantitativeDataFrame(df)
ids = IDS()
ids.fit(quant_df, cars, debug=False)
metrics = ids.score_interpretable_metrics(quant_df)
print(metrics)
import random
from collections import Counter
from pyarc.qcba import *
from pyarc.algorithms import createCARs, top_rules
from pyarc import TransactionDB
from pyids.ids_classifier import IDS, mine_IDS_ruleset, mine_CARs
from pyids.ids_cacher import IDSCacher
from pyids.ids_ruleset import IDSRuleSet
from pyids.ids_rule import IDSRule
from pyids.model_selection import encode_label, mode, RandomSearchOptimizer
df = pd.read_csv("./data/titanic.csv")
df["Died"] = df["Died"].astype(str) + "_"
cars = mine_CARs(df, 100)
quant_dataframe = QuantitativeDataFrame(df)
ids = IDS()
ids.fit(class_association_rules=cars,
quant_dataframe=quant_dataframe,
algorithm="DLS")
acc = ids.score_auc(quant_dataframe)
print(acc)
print(ids.clf.rules)
from pyids.ids_classifier import IDS, mine_IDS_ruleset
from pyids.ids_ruleset import IDSRuleSet
from pyids.model_selection import RandomSearchOptimizer, train_test_split_pd
from pyids.rule_mining import RuleMiner
df = pd.read_csv("../../data/titanic.csv")
rm = RuleMiner()
cars = rm.mine_rules(df, minsup=0.001)
ids_ruleset = IDSRuleSet.from_cba_rules(cars)
df_train, df_test = train_test_split_pd(df, prop=0.25)
quant_df_train, quant_df_test = QuantitativeDataFrame(
df_train), QuantitativeDataFrame(df_test)
random_optimizer = RandomSearchOptimizer(IDS(),
maximum_score_estimation_iterations=5,
maximum_iterations=500)
lambda_array = random_optimizer.fit(ids_ruleset, quant_df_train, quant_df_test)
all_params = random_optimizer.score_params_dict
print(lambda_array)
with open("results/random_search_lambda_array.txt", "w") as file:
file.write(str(lambda_array))
with open("results/random_search_all_score_params.txt", "w") as file:
file.write(str(random_optimizer.score_params_dict))
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import random
from collections import Counter
from pyarc.qcba import *
from pyarc.algorithms import createCARs, top_rules
from pyarc import TransactionDB
from pyids.ids_classifier import IDS, mine_IDS_ruleset
from pyids.ids_cacher import IDSCacher
from pyids.ids_ruleset import IDSRuleSet
from pyids.ids_rule import IDSRule
from pyids.model_selection import encode_label, mode, CoordinateAscentOptimizer
df = pd.read_csv("./data/titanic.csv")
ids_ruleset = mine_IDS_ruleset(df, rule_cutoff=40)
quant_dataframe = QuantitativeDataFrame(df)
coordinate_ascent = CoordinateAscentOptimizer(
IDS(),
debug=True,
maximum_delta_between_iterations=200,
maximum_score_estimation_iterations=3,
ternary_search_precision=20)
coordinate_ascent.fit(ids_ruleset, quant_dataframe, quant_dataframe)
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import random
from sklearn.metrics import accuracy_score, auc, roc_auc_score
from pyids.ids_rule import IDSRule
from pyids.ids_ruleset import IDSRuleSet
from pyids.ids_objective_function import ObjectiveFunctionParameters, IDSObjectiveFunction
from pyids.ids_optimizer import RSOptimizer, SLSOptimizer
from pyids.ids_cacher import IDSCacher
from pyids.ids_classifier import IDS, mine_CARs
from pyids.visualization import IDSVisualization
from pyarc.qcba import *
df = pd.read_csv("C:/code/python/interpretable_decision_sets/data/iris0.csv")
cars = mine_CARs(df, 20)
quant_df = QuantitativeDataFrame(df)
ids = IDS()
ids.fit(quant_df, cars, debug=True)
viz = IDSVisualization(ids, quant_df)
viz.visualize_dataframe()
import pandas as pd
from collections import Counter
from pyarc.qcba.data_structures import QuantitativeDataFrame
from pyids.ids_classifier import IDS, mine_CARs
df = pd.read_csv("./data/titanic.csv")
cars = mine_CARs(df, 20)
quant_dataframe = QuantitativeDataFrame(df)
ids = IDS()
ids.fit(quant_dataframe,
class_association_rules=cars,
debug=False,
algorithm="SLS")
acc = ids.score(quant_dataframe)