I'll fully admit that I may be setting up the conditional space wrong here but for some reason, I just can't get this to function at all. I am attempting to use hyperopt to tune a logistic regression model and depending on the solver there are some other parameters that need to be explored. If you choose the liblinear solver you can choose penalties, and depending on the penalty you can also choose dual. When I try and run hyperopt on this search space though, it keeps giving me an error because its passing the entire dictionary as show below. Any ideas?
The error I'm getting is
ValueError: Logistic Regression supports only liblinear, newton-cg, lbfgs and sag solvers, got {'solver': 'sag'}'
This format worked when setting up a random forest search space so I'm at a loss.
import numpy as np
import scipy as sp
import pandas as pd
pd.options.display.max_columns = None
pd.options.display.max_rows = None
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns
sns.set(style="white")
import pyodbc
import statsmodels as sm
from pandasql import sqldf
import math
from tqdm import tqdm
import pickle
from sklearn.preprocessing import RobustScaler, OneHotEncoder, MinMaxScaler
from sklearn.utils import shuffle
from sklearn.cross_validation import KFold, StratifiedKFold, cross_val_score, cross_val_predict, train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import StratifiedKFold as StratifiedKFoldIt
from sklearn.feature_selection import RFECV, VarianceThreshold, SelectFromModel, SelectKBest
from sklearn.decomposition import PCA, IncrementalPCA, FactorAnalysis
from sklearn.calibration import CalibratedClassifierCV
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier, GradientBoostingClassifier, AdaBoostClassifier, BaggingClassifier
from sklearn.svm import SVC
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB, MultinomialNB
from sklearn.linear_model import LogisticRegression, LogisticRegressionCV, SGDClassifier
from sklearn.metrics import precision_recall_curve, precision_score, recall_score, accuracy_score, classification_report, confusion_matrix, f1_score, log_loss
from imblearn.over_sampling import RandomOverSampler, SMOTE, ADASYN
from imblearn.under_sampling import RandomUnderSampler, ClusterCentroids, NearMiss, NeighbourhoodCleaningRule, OneSidedSelection
from xgboost.sklearn import XGBClassifier
from hyperopt import fmin, tpe, hp, Trials, STATUS_OK
space4lr = {
'C': hp.uniform('C', .0001, 100.0),
'solver' : hp.choice('solver', [
{'solver' : 'newton-cg',},
{'solver' : 'lbfgs',},
{'solver' : 'sag'},
{'solver' : 'liblinear', 'penalty' : hp.choice('penalty', [
{'penalty' : 'l1'},
{'penalty' : 'l2', 'dual' : hp.choice('dual', [True, False])}]
)},
]),
'fit_intercept': hp.choice('fit_intercept', ['True', 'False']),
'class_weight': hp.choice('class_weight', ['balanced', None]),
'max_iter': 50000,
'random_state': 84,
'n_jobs': 8
}
lab = 0
results = pd.DataFrame()
for i in feature_elims:
target = 'Binary_over_3'
alt_targets = ['year2_PER', 'year2_GP' ,'year2_Min', 'year2_EFF' ,'year2_WS/40' ,'year2_Pts/Poss' ,'Round' ,'GRZ_Pick'
,'GRZ_Player_Rating' ,'Binary_over_2', 'Binary_over_3' ,'Binary_over_4' ,'Binary_5' ,'Draft_Strength']
#alt_targets.remove(target)
nondata_columns = ['display_name' ,'player_global_id', 'season' ,'season_' ,'team_global_id', 'birth_date', 'Draft_Day']
nondata_columns.extend(alt_targets)
AGG_SET_CART_PERC = sqldf("""SELECT * FROM AGG_SET_PLAYED_ADJ_SOS_Jan1 t1
LEFT JOIN RANKINGS t2 ON t1.[player_global_id] = t2.[player_global_id]
LEFT JOIN Phys_Training t3 ON t1.[player_global_id] = t3.[player_global_id]""")
AGG_SET_CART_PERC['HS_RSCI'] = AGG_SET_CART_PERC['HS_RSCI'].fillna(110)
AGG_SET_CART_PERC['HS_Avg_Rank'] = AGG_SET_CART_PERC['HS_Avg_Rank'].fillna(1)
AGG_SET_CART_PERC['HS_years_ranked'] = AGG_SET_CART_PERC['HS_years_ranked'].fillna(0)
AGG_SET_CART_PERC = shuffle(AGG_SET_CART_PERC, random_state=8675309)
rus = RandomUnderSampler(random_state=8675309)
ros = RandomOverSampler(random_state=8675309)
rs = RobustScaler()
X = AGG_SET_CART_PERC
y = X[target]
X = pd.DataFrame(X.drop(nondata_columns, axis=1))
position = pd.get_dummies(X['position'])
for idx, row in position.iterrows():
if row['F/C'] == 1:
row['F'] = 1
row['C'] = 1
if row['G/F'] == 1:
row['G'] = 1
row['F'] = 1
position = position.drop(['F/C', 'G/F'], axis=1)
X = pd.concat([X, position], axis=1).drop(['position'], axis=1)
X = rs.fit_transform(X, y=None)
X = i.transform(X)
def hyperopt_train_test(params):
clf = LogisticRegression(**params)
#cvs = cross_val_score(xgbc, X, y, scoring='recall', cv=skf).mean()
skf = StratifiedKFold(y, n_folds=6, shuffle=False, random_state=1)
metrics = []
tuning_met = []
accuracy = []
precision = []
recall = []
f1 = []
log = []
for i, (train, test) in enumerate(skf):
X_train = X[train]
y_train = y[train]
X_test = X[test]
y_test = y[test]
X_train, y_train = ros.fit_sample(X_train, y_train)
X_train, y_train = rus.fit_sample(X_train, y_train)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
tuning_met.append((((precision_score(y_test, y_pred))*4) + recall_score(y_test, y_pred))/5)
accuracy.append(accuracy_score(y_test, y_pred))
precision.append(precision_score(y_test, y_pred))
recall.append(recall_score(y_test, y_pred))
f1.append(f1_score(y_test, y_pred))
log.append(log_loss(y_test, y_pred))
metrics.append(sum(tuning_met) / len(tuning_met))
metrics.append(sum(accuracy) / len(accuracy))
metrics.append(sum(precision) / len(precision))
metrics.append(sum(recall) / len(recall))
metrics.append(sum(f1) / len(f1))
metrics.append(sum(log) / len(log))
return(metrics)
best = 0
count = 0
def f(params):
global best, count, results, lab, met
met = hyperopt_train_test(params.copy())
met.append(params)
met.append(featureset_labels[lab])
acc = met[0]
results = results.append([met])
if acc > best:
print(featureset_labels[lab],'new best:', acc, 'Accuracy:', met[1], 'Precision:', met[2], 'Recall:', met[3], 'using', params, """
""")
best = acc
else:
print(acc, featureset_labels[lab], count)
count = count + 1
return {'loss': -acc, 'status': STATUS_OK}
trials = Trials()
best = fmin(f, space4lr, algo=tpe.suggest, max_evals=1000, trials=trials)
print(featureset_labels[lab], ' best:')
print(best, """
""")
lab = lab + 1
sagsolver. – Topographer