def handle(self, *args, **kwargs):
# get model
TARGET_MODEL = 5
job = Job.objects.filter(pk=TARGET_MODEL)[0]
model = joblib.load(job.predictive_model.model_path)
model = model[0]
training_df, test_df = get_encoded_logs(job)
feature_names = list(
training_df.drop(['trace_id', 'label'], 1).columns.values)
X_train = training_df.drop(['trace_id', 'label'], 1)
Y_train = training_df.drop(
['trace_id', 'prefix_1', 'prefix_3', 'prefix_4', 'label'], 1)
rf = RuleFit()
columns = list(X_train.columns)
X = X_train.as_matrix()
rf.fit(X, Y_train.values.ravel(), feature_names=columns)
rules = rf.get_rules()
# rules = rules[rules.coef != 0].sort_values("support", ascending=False)
rules = rules[(rules.coef > 0.) & (rules.type != 'linear')]
rules['effect'] = rules['coef'] * rules['support']
pd.set_option('display.max_colwidth', -1)
rules.nlargest(10, 'effect')
# print(rules)
rules
def train_job(train_idx, test_idx, t_size, rf_mode, m_rules, r_seed, X, y,
feas, n_samples):
"""
每个 fold 中进行训练和验证
"""
p = current_process()
print('process counter:', p._identity[0], 'pid:', os.getpid())
# 初始化 estimator 训练集进入模型
rf = RuleFit(tree_size=t_size,
rfmode=rf_mode,
max_rules=m_rules,
random_state=r_seed)
print(
"\nTree generator:{0}, \n\nMax rules:{1}, Tree size:{2}, Random state:{3}"
.format(rf.tree_generator, rf.max_rules, rf.tree_size,
rf.random_state))
rf.fit(X[train_idx], y[train_idx], feas)
# 验证测试集 (通过 index 去除 fake data)
real_test_index = test_idx[test_idx < n_samples]
batch_test_x = X[real_test_index]
batch_test_y = y[real_test_index]
batch_test_size = len(real_test_index)
y_pred = rf.predict(batch_test_x)
# 计算测试集 ACC
accTest = accuracy_score(batch_test_y, y_pred)
print("\nTest Accuracy:", "{:.6f}".format(accTest), "Test Size:",
batch_test_size)
print(
"\n========================================================================="
)
# 返回测试集和预测结果用于统计
return batch_test_y, y_pred
def __init__(
self,
mode,
max_depth=3,
feature_names=None,
max_sentences=20000,
exp_rand_tree_size=True,
tree_generator=None,
):
'''
mode: 'classify' or 'regress'
max_depth: maximum depth of trained trees
feature_names: names of features
max_sentences: maximum number of extracted sentences
exp_rand_tree_size: Having trees with different sizes
tree_generator: Tree generator model (overwrites above features)
'''
self.feature_names = feature_names
self.mode = mode
max_leafs = 2**max_depth
num_trees = max_sentences // max_leafs
if tree_generator is None:
tree_generator = RandomForestClassifier(num_trees,
max_depth=max_depth)
self.exp_rand_tree_size = exp_rand_tree_size
self.rf = RuleFit(rfmode=mode,
tree_size=max_leafs,
max_rules=max_sentences,
tree_generator=tree_generator,
exp_rand_tree_size=True,
fit_lasso=False,
Cs=10.**np.arange(-4, 1),
cv=3)
def _getRulesRulefit(df_aux, model_params):
# Prepare data
X_train = df_aux[feature_cols]
y_train = df_aux["predictions"]
# Fit model
if "tree_size" not in model_params.keys():
model_params["tree_size"] = len(feature_cols) * 2
if "rfmode" not in model_params.keys():
model_params["rfmode"] = "classify"
rf = RuleFit(**model_params)
rf.fit(X_train.values, y_train.values, feature_names=feature_cols)
# Get rules
print("Obtaining Rules using RuleFit...")
rules_all = rf.get_rules()
rules_all = rules_all[rules_all.coef != 0]
rules_all = rules_all[rules_all.importance > 0].sort_values(
"support", ascending=False)
rules_all = rules_all[rules_all.coef > 0]
rules_all = rules_all.sort_values("support", ascending=False)
rules_all = rules_all[rules_all["type"] == "rule"]
rules_all["size_rules"] = rules_all.apply(
lambda x: len(x["rule"].split("&")), axis=1)
# Turn list of rules to dataframe
print("Turning rules to hypercubes...")
df_rules = turn_rules_to_df(list_rules=list(rules_all["rule"].values),
list_cols=feature_cols)
# Get corresponding rule size from the original rule extraction model,
# not on the hypercubes obtained later
df_rules["size_rules"] = list(rules_all["size_rules"].values)
# Prune rules
if simplify_rules:
print("Prunning the rules obtained...")
df_rules_pruned = df_rules.drop(columns=["size_rules"]).copy()
df_rules_pruned = simplifyRules(df_rules_pruned, categorical_cols)
df_rules_pruned = df_rules_pruned.reset_index().merge(
df_rules.reset_index()[["index", "size_rules"]], how="left")
df_rules_pruned.index = df_rules_pruned["index"]
df_rules_pruned = df_rules_pruned.drop(columns=["index"],
errors="ignore")
df_rules = df_rules_pruned
return df_rules
def __init__(self,
mode,
max_depth=3,
feature_names=None,
max_rules=20000,
exp_rand_tree_size=True,
Cs=None,
cv=None,
tree_generator=None):
super().__init__(mode,
max_depth=3,
feature_names=None,
max_rules=20000,
exp_rand_tree_size=True,
Cs=None,
cv=None,
tree_generator=None)
if Cs is None:
Cs = 10.**np.arange(-4, 1)
if cv is None:
cv = 3
self.feature_names = feature_names
self.mode = mode
max_leafs = 2**max_depth
num_trees = max_rules // max_leafs
if tree_generator is None:
tree_generator = RandomForestClassifier(num_trees,
max_depth=max_depth)
self.exp_rand_tree_size = exp_rand_tree_size
self.rf = RuleFit(rfmode=mode,
tree_size=max_leafs,
max_rules=max_rules,
tree_generator=tree_generator,
exp_rand_tree_size=True,
fit_lasso=False,
Cs=Cs,
cv=cv)
import numpy as np
import pandas as pd
from sklearn.ensemble import GradientBoostingRegressor
from rulefit import RuleFit
boston_data = pd.read_csv("boston.csv", index_col=0)
y = boston_data.medv.values
X = boston_data.drop("medv", axis=1)
features = X.columns
X = X.as_matrix()
gb = GradientBoostingRegressor(n_estimators=100,
max_depth=3,
learning_rate=0.01)
rf = RuleFit(gb)
rf.fit(X, y, feature_names=features)
rules = rf.get_rules()
rules = rules[rules.coef != 0].sort("support")
# 交叉验证
rs = KFold(n_splits=args.kfolds,
shuffle=True,
random_state=args.randomseed)
# 生成 k-fold 训练集、测试集索引
cv_index_set = rs.split(y)
k_fold_step = 1 # 初始化折数
# 暂存每次选中的测试集和对应预测结果
test_cache = pred_cache = np.array([], dtype=np.int)
# 迭代训练 k-fold 交叉验证
for train_index, test_index in cv_index_set:
print("\nFold:", k_fold_step)
# 初始化 estimator 训练集进入模型
rf = RuleFit(tree_size=args.treesize,
rfmode=args.rfmode,
max_rules=args.maxrules,
random_state=args.randomseed)
rf.fit(X[train_index], y[train_index], features)
# 测试集验证
y_pred = rf.predict(X[test_index])
# 计算测试集 ACC
accTest = accuracy_score(y[test_index], y_pred)
print("\nFold:", k_fold_step, "Test Accuracy:",
"{:.6f}".format(accTest), "Test Size:", test_index.size)
# 暂存每次选中的测试集和预测结果
test_cache = np.concatenate((test_cache, y[test_index]))
pred_cache = np.concatenate((pred_cache, y_pred))
print(
"\n========================================================================="
)
# 每个fold训练结束后次数 +1
rgb = RuleFit(Cs=None,
cv=3,
exp_rand_tree_size=True,
lin_standardise=True,
lin_trim_quantile=0.025,
max_rules=2000,
memory_par=0.01,
model_type='rl',
random_state=None,
rfmode='regress',
sample_fract='default',
tree_generator=GradientBoostingRegressor(
alpha=0.9,
criterion='friedman_mse',
init=None,
learning_rate=0.02,
loss='ls',
max_depth=100,
max_features=None,
max_leaf_nodes=15,
min_impurity_decrease=0.0,
min_impurity_split=None,
min_samples_leaf=1,
min_samples_split=2,
min_weight_fraction_leaf=0.0,
n_estimators=500,
n_iter_no_change=None,
presort='auto',
random_state=572,
subsample=0.46436099318265595,
tol=0.0001,
validation_fraction=0.1,
verbose=0,
warm_start=False),
tree_size=3)
from sklearn.ensemble import GradientBoostingRegressor,GradientBoostingClassifier, RandomForestClassifier, RandomForestRegressor
from rulefit import RuleFit
boston_data = pd.read_csv("boston.csv", index_col=0)
y = boston_data.medv.values
X = boston_data.drop("medv", axis=1)
features = X.columns
X = X.values
typ = 'regressor' #regressor or classifier
if typ == 'regressor':
rf = RuleFit(
rfmode='regress',
tree_generator=RandomForestRegressor()
)
rf.fit(X, y, feature_names=features)
y_pred = rf.predict(X)
insample_rmse = np.sqrt(np.sum((y_pred - y)**2)/len(y))
elif typ == 'classifier':
y_class = y.copy()
y_class[y_class < 21] = -1
y_class[y_class >= 21] = +1
N = X.shape[0]
rf = RuleFit( rfmode='classify',
tree_generator=RandomForestClassifier()
)
rf.fit(X, y_class, feature_names=features)
y_pred = rf.predict(X)
y_proba = rf.predict_proba(X)
# -*- coding: utf-8 -*-
"""
Created on Sun Nov 25 23:54:35 2018
@author: Melanie
"""
import numpy as np
import pandas as pd
from rulefit import RuleFit
boston_data = pd.read_csv("prism_numeric.csv", index_col=0)
y = boston_data.medv.values
X = boston_data.drop("medv", axis=1)
features = X.columns
X = X.as_matrix()
rf = RuleFit()
rf.fit(X, y, feature_names=features)
rf.predict(X)
rules = rf.get_rules()
rules = rules[rules.coef != 0].sort_values("support", ascending=False)
print(rules)
boston_data = pd.read_csv("boston.csv", index_col=0)
y = boston_data.medv.values
X = boston_data.drop("medv", axis=1)
features = X.columns
X = X.as_matrix()
typ = 'classifier' #regressor or classifier
if typ == 'regressor':
rf = RuleFit(tree_size=4,
sample_fract='default',
max_rules=2000,
memory_par=0.01,
tree_generator=None,
rfmode='regress',
lin_trim_quantile=0.025,
lin_standardise=True,
exp_rand_tree_size=True,
random_state=1)
rf.fit(X, y, feature_names=features)
y_pred = rf.predict(X)
insample_rmse = np.sqrt(np.sum((y_pred - y)**2) / len(y))
elif typ == 'classifier':
y_class = y.copy()
y_class[y_class < 21] = -1
y_class[y_class >= 21] = +1
N = X.shape[0]
rf = RuleFit(tree_size=4,
sample_fract='default',
max_rules=2000,
data = np.load('data.npy')
target = np.load('target.npy')
feature_name = ['QNH', 'TEMP', 'RH', 'absolute_temp', 'WS2A', 'CW2A']
train = data[200:, :]
test = data[:200, :]
train_target = target[200:]
test_target = target[:200]
from sklearn.ensemble import GradientBoostingRegressor
gb = GradientBoostingRegressor(n_estimators=500,
max_depth=10,
learning_rate=0.01)
relu_fit = RuleFit()
relu_fit.max_iter = 4000
relu_fit.tree_generator = gb
relu_fit.fit(train, train_target, feature_names=feature_name)
f = relu_fit.predict(test)
ff = relu_fit.predict(train)
rule = relu_fit.get_rules()
truth = 0
for i in range(test_target.shape[0]):
if abs(test_target[i] - f[i]) / test_target[i] < 0.1:
truth += 1
print("truth: ", truth / test_target.shape[0])
#print(rule)
ruleset = pd.DataFrame(data=rule)
writer = pd.ExcelWriter('./rules.xlsx')
def fitrf(train, labels):
r = RuleFit()
r.fit(train, labels)
return r
