import re
from data_helper.names import keys, get_filename
from data_helper.features import Condition, FeatureException
import numpy as np
from operator import itemgetter
import settings
import matplotlib.pyplot as plt
from util.files import Exporter
conditions = {}
for key in keys():
if len(re.findall('_', key)) == 2:
fname = get_filename(key)
try:
ConditionStats = Condition(import_dir=settings.CLUSTER_DIR).load(fname, remove_outliers=True).make_condition_stats()
except FeatureException as e:
print str(e)
else:
stats = ConditionStats.condition_stats('usa')
for condition, val in stats.iteritems():
try:
conditions[condition] = conditions[condition] + val['prices_centered']
except KeyError:
try:
conditions[condition] = val['prices_centered']
except KeyError:
pass
results = []
for condition, offset in conditions.iteritems():
results.append([float(condition), np.average(offset)])
def test(FID, show_price_pairs=default_show_price_pairs, retrain=True):
dataset, price_mmr_state_condition_vin = get_dataset(
get_filename(FID),
remove_initial_outliers=False,
extra_continuous_exclusions=EXTRA_CONTINUOUS_EXCLUSIONS,
extra_categorical_exclusions=EXTRA_CATEGORICAL_EXCLUSIONS,
expand_odometer=True,
capture_condition=True,
capture_state=True)
vec = DictVectorizer()
vectors = vec.fit_transform(dataset).toarray()
features = vec.get_feature_names()
# print features
# create a testing set
X_train, X_test, y_train, y_test = train_test_split(
vectors, price_mmr_state_condition_vin, test_size=0.3)
price_train = [p[0] for p in y_train]
###############################################################################
# IDEAL
# n_samples > n_features ** 2
sample_size = len(X_train)
min_sample_size = len(features) ** 2
print 'training set: %s samples, %s features^2' % (sample_size, min_sample_size)
# get the best classifier for the original full set of data
best_clf = train(X_train, price_train)
# predict targets on the same set of data
predicted_y, _, _ = predict.run(best_clf, X_train, y_train, show_prices=False)
if retrain:
# remove the worst performers and consider them outliers
X_train, y_train = filter_worst(X_train, y_train, predicted_y)
price_train = [p[0] for p in y_train]
# retrain the model
best_clf = train(X_train, price_train)
sample_size = len(X_train)
min_sample_size = len(features) ** 2
print '\ntraining set (outliers removed): %s samples, %s features^2' % (sample_size, min_sample_size)
if sample_size > min_sample_size:
print 'sufficient sample to feature ratio'
else:
print 'WARN - insufficient sample to feature ratio to be highly confident of fit'
# n_samples > n_features ** 2
price_test = [p[0] for p in y_test]
# scores = cross_val_score(best_clf, vectors, selling_prices, cv=5, scoring='r2')
scores = cross_val_score(best_clf, X_test, price_test, cv=5, scoring='r2')
print 'Grid Search Results'
print "Accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() * 2)
_, score, explained_variance = predict.run(best_clf,
X_test, y_test, offset_state=False, offset_condition=False, show_prices=show_price_pairs)
print 'held out test sample results:'
print 'test r^2 score: %s' % score
print 'test explained variance: %s' % explained_variance
print '\n'
