import pandas as pd
import numpy as np
from pyids import IDS
from pyids.algorithms import mine_CARs
from pyids.data_structures import IDSRuleSet
import json
from pyarc.qcba.data_structures import QuantitativeDataFrame
import random
import logging
import time
logging.basicConfig(level=logging.INFO)
df = pd.read_csv("../../../data/iris0.csv")
cars = mine_CARs(df, 10, sample=False)
ids_ruleset = IDSRuleSet.from_cba_rules(cars).ruleset
quant_dataframe = QuantitativeDataFrame(df)
def generate_lambda_arr(one_idx):
total_params = 7
if one_idx == 0:
start_arr = []
else:
start_arr = one_idx * [0]
end_arr = (total_params - one_idx - 1) * [0]
data_count = df.shape[0]
quant_df = QuantitativeDataFrame(df)
for algorithm in ["DLS", "SLS", "DUSM", "RUSM"]:
durations = []
for _ in range(time_estimation_iterations):
print(_)
lambda_array = generate_lambda_array()
print(f"data count: {data_count}")
print(f"algorithm: {algorithm}")
print(f"using lambda: {lambda_array}")
cars = mine_CARs(df, rule_cutoff=rule_cutoff)
ids = IDS(algorithm=algorithm)
start = time.time()
ids.fit(class_association_rules=cars,
quant_dataframe=quant_df,
lambda_array=lambda_array)
duration = time.time() - start
print(f"avg duration: {duration}")
durations.append(duration)
duration = np.mean(durations)
print(f"avg duration: {duration}")
from pyids.model_selection.random_search import RandomSearch
from pyids.algorithms.ids import IDS
from pyids.algorithms import mine_CARs
from pyarc.qcba.data_structures import QuantitativeDataFrame
import pandas as pd
import numpy as np
df_iris = pd.read_csv("../../../data/iris0.csv")
quant_df = QuantitativeDataFrame(df_iris)
cars = mine_CARs(df_iris, 40)
def is_solution_interpretable(metrics):
print(metrics)
return (metrics["fraction_overlap"] <= 0.3
and metrics["fraction_classes"] > 1.0
and metrics["fraction_uncovered"] <= 0.3
and metrics["average_rule_width"] < 8
and metrics["ruleset_length"] <= 10)
def solution_interpretability_distance(metrics):
distance_vector = np.array([
max(metrics["fraction_overlap"] - 0.1, 0),
max(1 - metrics["fraction_classes"], 0),
max(metrics["fraction_uncovered"] - 0.15, 0),
max(metrics["average_rule_width"] - 8, 0),
max(metrics["ruleset_length"] - 10, 0)
])
from pyids.model_selection import CoordinateAscent
from pyids.algorithms.ids import IDS
from pyids.algorithms import mine_CARs, mine_IDS_ruleset
from pyarc.qcba.data_structures import QuantitativeDataFrame
import pandas as pd
import numpy as np
df_iris = pd.read_csv("../../../data/iris0.csv")
quant_df = QuantitativeDataFrame(df_iris)
cars = mine_CARs(df_iris, 30)
interpretability_bounds = dict(fraction_overlap=0.1,
fraction_classes=1,
fraction_uncovered=0.35,
average_rule_width=8,
ruleset_length=10)
def is_solution_interpretable(metrics):
print(metrics)
return (metrics["fraction_overlap"] <=
interpretability_bounds["fraction_overlap"]
and metrics["fraction_classes"] >=
interpretability_bounds["fraction_classes"]
and metrics["fraction_uncovered"] <=
interpretability_bounds["fraction_uncovered"]
and metrics["average_rule_width"] <=
interpretability_bounds["average_rule_width"]
and metrics["ruleset_length"] <=
from pyids.algorithms import mine_CARs
from pyids.algorithms.ids_multiclass import IDSOneVsAll
from pyids.data_structures import IDSRuleSet
from pyarc.qcba.data_structures import QuantitativeDataFrame
from pyarc.data_structures import TransactionDB
from pyarc import CBA
import random
import logging
import time
import matplotlib.pyplot as plt
df = pd.read_csv("c:/code/python/machine_learning/assoc_rules/train/iris0.csv")
cars = mine_CARs(df, rule_cutoff=40)
quant_dataframe = QuantitativeDataFrame(df)
def is_solution_interpretable(metrics):
print(metrics)
return (
metrics["fraction_overlap"] <= 0.10 and
metrics["fraction_classes"] > 1.0 and
metrics["fraction_uncovered"] <= 0.15 and
metrics["average_rule_width"] < 8 and
metrics["ruleset_length"] <= 10
)
def solution_interpretability_distance(metrics):
distance_vector = np.array([
from pyids.model_selection import CoordinateAscent
from pyids.algorithms.ids import IDS
from pyids.algorithms import mine_CARs, mine_IDS_ruleset
from pyarc.qcba.data_structures import QuantitativeDataFrame
import pandas as pd
import numpy as np
df_iris = pd.read_csv("../../../data/iris0.csv")
quant_df = QuantitativeDataFrame(df_iris)
cars = mine_CARs(df_iris, 20)
interpretability_bounds = dict(fraction_overlap=0.1,
fraction_classes=1,
fraction_uncovered=0.35,
average_rule_width=8,
ruleset_length=10)
def is_solution_interpretable(metrics):
print(metrics)
return (metrics["fraction_overlap"] <=
interpretability_bounds["fraction_overlap"]
and metrics["fraction_classes"] >=
interpretability_bounds["fraction_classes"]
and metrics["fraction_uncovered"] <=
interpretability_bounds["fraction_uncovered"]
and metrics["average_rule_width"] <=
interpretability_bounds["average_rule_width"]
and metrics["ruleset_length"] <=
from pyids.algorithms.ids import IDS
from pyids.algorithms import mine_CARs
from pyarc.qcba.data_structures import QuantitativeDataFrame
from pyids.model_selection.coordinate_ascent import CoordinateAscent
lambda_dict = {
'l1': 124.16415180612711,
'l2': 38.896662094192955,
'l3': 557.0996799268405,
'l4': 638.188385916781,
'l5': 136.48056698673983,
'l6': 432.1760402377687,
'l7': 452.1563786008231
}
lambda_array = [
665.9341563786008, 271.7242798353909, 212.34156378600824,
20.489711934156375, 648.5761316872428, 911, 560
]
df = pd.read_csv("C:/code/python/machine_learning/assoc_rules/train/iris0.csv")
quant_df = QuantitativeDataFrame(df)
quant_df_test = QuantitativeDataFrame(
pd.read_csv("C:/code/python/machine_learning/assoc_rules/test/iris0.csv"))
cars = mine_CARs(df, 20)
ids = IDS(algorithm="DUSM")
ids.fit(quant_df, cars, lambda_array=lambda_array)
print(ids.score_auc(quant_df))