def __init__(self, calibrationTable, score_func=accuracy_score):
"""
calibrate a classifier
@param calibrationTable: a pandas data frame
"""
print '--------- Calibrating Imputer -----------'
X_cal, y_cal, _, _ = impute_risk_factors(calibrationTable)
bestScore = -1
bestPipe = None
bestParams = None
for name, (pipe, params) in make_pipes().iteritems():
print '>'*10, name, '<'*10
_, cur_bestParams, cur_bestScore = fitClfWithGridSearch(
name + '_risk', pipe, params, DatasetPair(np.array(X_cal), y_cal),
saveToDir='/home/jj/code/Kaggle/allstate/output/gridSearchOutput',
useJJ=True, score_func=score_func, n_jobs=N_JOBS, verbosity=0,
minimize=False, cvSplitNum=5,
maxLearningSteps=10,
numConvergenceSteps=4, convergenceTolerance=0, eliteProportion=0.1,
parentsProportion=0.4, mutationProportion=0.1, mutationProbability=0.1,
mutationStdDev=None, populationSize=6)
if cur_bestScore > bestScore:
bestScore = cur_bestScore
bestPipe = clone(pipe)
bestPipe.set_params(**cur_bestParams)
bestParams = cur_bestParams
print '----> best score:', bestScore
pprint(bestParams)
self._imputer = bestPipe
# plot_feature_importances(X_train, outputTable, inputTable.columns)
print '----------- individual accuracy score'
indivClfs = []
for col in outputTable_cal.columns:
print '>'*20, col, '<'*20
cur_y = np.array(outputTable_cal[col])
bestScore = -1
bestPipe = None
bestParams = None
for name, (pipe, params) in make_pipes().iteritems():
print '>'*10, name, '<'*10
_, cur_bestParams, cur_bestScore = fitClfWithGridSearch(
'_'.join([name, col, calibrationName]), pipe, params, DatasetPair(X_cal, cur_y),
saveToDir='/home/jj/code/Kaggle/allstate/output/gridSearchOutput',
useJJ=True, score_func=accuracy_score, n_jobs=N_JOBS, verbosity=0,
minimize=False, cvSplitNum=5,
maxLearningSteps=10,
numConvergenceSteps=4, convergenceTolerance=0, eliteProportion=0.1,
parentsProportion=0.4, mutationProportion=0.1, mutationProbability=0.1,
mutationStdDev=None, populationSize=6)
if cur_bestScore > bestScore:
bestScore = cur_bestScore