def evalOne(parameters):
all_obs = []
all_pred = []
for location in locations:
trainX, testX, trainY, testY = splitDataForXValidation(
location, "location", data, all_features, "target")
if "depth" in parameters:
model = RandomForestRegressor(
max_depth=parameters["depth"],
random_state=42,
n_estimators=parameters["n_estimators"],
n_jobs=-1)
elif "leaf" in parameters:
model = RandomForestRegressor(
min_samples_leaf=parameters["leaf"],
random_state=42,
n_estimators=parameters["n_estimators"],
n_jobs=-1)
elif "max_leaf" in parameters:
model = RandomForestRegressor(
max_leaf_nodes=parameters["max_leaf"],
random_state=42,
n_estimators=parameters["n_estimators"],
n_jobs=-1)
model.fit(trainX, trainY)
prediction = model.predict(testX)
all_obs.extend(testY)
all_pred.extend(prediction)
return rmseEval(all_obs, all_pred)[1]
def test_boston_housing_load_save_valid(self):
(x_train, y_train), (x_test, y_test) = TestUtil.get_boston_housing()
explained_model = RandomForestRegressor(n_estimators=64, max_depth=5, random_state=1)
explained_model.fit(x_train, y_train)
model_builder = MLPModelBuilder(num_layers=2, num_units=32, activation="relu", p_dropout=0.2, verbose=0,
batch_size=32, learning_rate=0.001, num_epochs=2, early_stopping_patience=128)
masking_operation = ZeroMasking()
loss = mean_squared_error
num_models_settings = [1, 2]
for num_models in num_models_settings:
explainer = CXPlain(explained_model, model_builder, masking_operation, loss,
num_models=num_models)
explainer.fit(x_train, y_train)
median_1 = explainer.predict(x_test)
tmp_dir_name = tempfile.mkdtemp()
explainer.save(tmp_dir_name)
with self.assertRaises(ValueError):
explainer.save(tmp_dir_name, overwrite=False)
explainer.save(tmp_dir_name, overwrite=True)
explainer.load(tmp_dir_name)
median_2 = explainer.predict(x_test)
self.assertTrue(np.array_equal(median_1, median_2))
shutil.rmtree(tmp_dir_name) # Cleanup.
def test_boston_housing_valid(self):
(x_train, y_train), (x_test, y_test) = TestUtil.get_boston_housing()
explained_model = RandomForestRegressor(n_estimators=64,
max_depth=5,
random_state=1)
explained_model.fit(x_train, y_train)
model_builder = MLPModelBuilder(num_layers=2,
num_units=32,
activation="relu",
p_dropout=0.2,
verbose=0,
batch_size=32,
learning_rate=0.001,
num_epochs=2,
early_stopping_patience=128)
masking_operation = ZeroMasking()
loss = mean_squared_error
explainer = CXPlain(explained_model, model_builder, masking_operation,
loss)
explainer.fit(x_train, y_train)
self.assertEqual(explainer.prediction_model.output_shape,
(None, np.prod(x_test.shape[1:])))
eval_score = explainer.score(x_test, y_test)
train_score = explainer.get_last_fit_score()
median = explainer.predict(x_test)
self.assertTrue(median.shape == x_test.shape)
def eval_one(step):
if step in cached_results:
return cached_results[step]
eval_features = []
for i in range(0, len(all_features)):
if step[i]:
eval_features.append(all_features[i])
all_predictions = []
all_observations = []
for location in locations:
trainX, testX, trainY, testY = splitDataForXValidation(location, "location", data, eval_features, "target")
model = RandomForestRegressor(min_samples_leaf = 2, random_state=42, n_estimators=650, n_jobs=-1)
model.fit(trainX, trainY)
predictions = model.predict(testX)
all_observations.extend(testY)
all_predictions.extend(predictions)
rmse = rmseEval(all_observations, all_predictions)[1]
cached_results[step] = rmse
# save down the cached result
cache_output = open(CACHE_FILE, "a")
step_list = [str(s) for s in step]
step_str = ",".join(step_list)
cache_output.write(str(rmse) + ";" + step_str + "\n")
cache_output.close()
return rmse
def post(self):
# upload audio file in server
voice = self.request.files["audio"][0]
extn = os.path.splitext(voice['filename'])[1]
fnm = os.path.splitext(voice['filename'])[0]
cname = str(uuid.uuid4()) + extn
fh = open(__UPLOADS__ + cname, 'w')
fh.write(voice['body'])
fh.close()
# get features from the audio file
attr = getAttributes(cname)
fdf = mongoTolist(False)
train = fdf[:,:-1]
target = fdf[:,-1]
#RandomForest Regression
rf = RandomForestRegressor(n_estimators = 506, n_jobs = -1)
rf.fit(train, target)
updrs_val = rf.predict([attr])
attr.append(updrs_val[0])
# get the theta from database
theta = list(db.theta.find({}))
theta1 = theta[0]["theta1"]
theta2 = theta[1]["theta2"]
# check is the person has Parkinson's Disease
isParkinson = octave.classify(theta1, theta2, np.array(attr))
self.render("output.html", ipk = isParkinson, updrs = updrs_val[0])
class RandomForestRegressorImpl():
def __init__(self, n_estimators=10, criterion='mse', max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features='auto', max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, bootstrap=True, oob_score=False, n_jobs=None, random_state=None, verbose=0, warm_start=False):
self._hyperparams = {
'n_estimators': n_estimators,
'criterion': criterion,
'max_depth': max_depth,
'min_samples_split': min_samples_split,
'min_samples_leaf': min_samples_leaf,
'min_weight_fraction_leaf': min_weight_fraction_leaf,
'max_features': max_features,
'max_leaf_nodes': max_leaf_nodes,
'min_impurity_decrease': min_impurity_decrease,
'min_impurity_split': min_impurity_split,
'bootstrap': bootstrap,
'oob_score': oob_score,
'n_jobs': n_jobs,
'random_state': random_state,
'verbose': verbose,
'warm_start': warm_start}
def fit(self, X, y=None):
self._sklearn_model = SKLModel(**self._hyperparams)
if (y is not None):
self._sklearn_model.fit(X, y)
else:
self._sklearn_model.fit(X)
return self
def predict(self, X):
return self._sklearn_model.predict(X)
def eval_one(min_samples_leaf, n_estimators):
log("min_samples_leaf: " + str(min_samples_leaf) + ", n_estimators: " +
str(n_estimators))
all_observations = []
all_pred_ALL = []
for group in range(0, len(groups)):
trainStations = []
for i in range(0, len(groups)):
if i != group:
trainStations.extend(groups[i])
testStations = groups[group]
train_station_set = set([float(s) for s in trainStations])
test_station_set = set([float(s) for s in testStations])
trainX, testX, trainY, testY = splitDataForXValidation(
train_station_set, test_station_set, "location", data,
all_features, "target")
model = RandomForestRegressor(min_samples_leaf=min_samples_leaf,
n_estimators=n_estimators,
n_jobs=-1,
random_state=42)
model.fit(trainX, trainY)
prediction_ALL = model.predict(testX)
rmse = rmseEval(testY, prediction_ALL)[1]
log("\tALL rmse: " + str(rmse))
all_observations.extend(testY)
all_pred_ALL.extend(prediction_ALL)
rmse = rmseEval(all_observations, all_pred_ALL)[1]
log("\tALL rmse:" + str(rmse))
return rmse
def test_boston_housing_no_fit_invalid(self):
(x_train, y_train), (x_test, y_test) = TestUtil.get_boston_housing()
explained_model = RandomForestRegressor(n_estimators=64,
max_depth=5,
random_state=1)
explained_model.fit(x_train, y_train)
model_builder = MLPModelBuilder(num_layers=2,
num_units=32,
activation="relu",
p_dropout=0.2,
verbose=0,
batch_size=32,
learning_rate=0.001,
num_epochs=2,
early_stopping_patience=128)
masking_operation = ZeroMasking()
loss = mean_squared_error
explainer = CXPlain(explained_model, model_builder, masking_operation,
loss)
with self.assertRaises(AssertionError):
explainer.predict(x_test, y_test)
with self.assertRaises(AssertionError):
explainer.score(x_test, y_test)
def trainRandomForest(data, columns, targetColumn, parameters):
modelColumns = []
for column in columns:
if column != targetColumn:
modelColumns.append(column)
modelData = []
for i in range(0, len(data[targetColumn])):
record = []
for column in modelColumns:
record.append(data[column][i])
modelData.append(record)
if "depth" in parameters:
model = RandomForestRegressor(max_depth=parameters["depth"],
n_estimators=parameters["estimators"],
n_jobs=-1,
random_state=42)
elif "leaf" in parameters:
model = RandomForestRegressor(min_samples_leaf=parameters["leaf"],
n_estimators=parameters["estimators"],
n_jobs=-1,
random_state=42)
model.fit(modelData, data[targetColumn])
return RandomForestModel(model, modelColumns)
def RandomForest(x_train,y_train,x_test,degree):
params = {'n_estimators': 1000, 'max_depth': degree, 'min_samples_split': 1,'warm_start':True}
clf = RandomForestRegressor(**params)
clf.fit(x_train, y_train)
y_predict = clf.predict(x_test)
#plt.plot(x_test,y_predict,color='red')
return y_predict
def randomforestregressor(self, testlen, ntrain, ntrees, nodes):
hsmadata = self.hsmadata
dates = pd.Series(hsmadata['date'].unique()).sort_values()
dates.index = range(0, len(dates))
ntest = len(dates) // testlen
hsma = pd.DataFrame()
for i in range(ntrain, ntest):
traindata = hsmadata[
(hsmadata['date'] >= dates[(i - ntrain) * testlen])
& (hsmadata['date'] < dates[i * testlen - self.day])].copy()
testdata = hsmadata[(hsmadata['date'] >= dates[i * testlen]) & (
hsmadata['date'] < dates[(i + 1) * testlen])].copy()
traindata = traindata.iloc[:, 2:]
traindatax = traindata.drop(['closeratio'], 1)
traindatay = traindata['closeratio']
testdatax = testdata[traindatax.columns]
treemodel = RandomForestRegressor(
n_estimators=ntrees,
min_samples_split=nodes * 2,
min_samples_leaf=nodes)
treemodel.fit(traindatax, traindatay)
testdata['predratio'] = treemodel.predict(testdatax)
hsma = pd.concat([hsma, testdata], ignore_index=True)
return (hsma)
def test_shap_summary(self):
data = self.iris.copy()
widget = self.widget
rf = SKL_RF(n_estimators=10)
model = RandomForestRegressor(rf)
rf.fit(data.X, data.Y)
#self.send_signals([(widget.Inputs.data, data), (widget.Inputs.model, model)])
def test_boston_housing_confidence_level_invalid(self):
(x_train, y_train), (x_test, y_test) = TestUtil.get_boston_housing()
explained_model = RandomForestRegressor(n_estimators=64,
max_depth=5,
random_state=1)
explained_model.fit(x_train, y_train)
model_builder = MLPModelBuilder(num_layers=2,
num_units=32,
activation="relu",
p_dropout=0.2,
verbose=0,
batch_size=32,
learning_rate=0.001,
num_epochs=3,
early_stopping_patience=128)
masking_operation = ZeroMasking()
loss = mean_squared_error
num_models = 2
explainer = CXPlain(explained_model,
model_builder,
masking_operation,
loss,
num_models=num_models)
explainer.fit(x_train, y_train)
invalid_confidence_levels = [1.01, -0.5, -0.01]
for confidence_level in invalid_confidence_levels:
with self.assertRaises(ValueError):
explainer.predict(x_test, confidence_level=confidence_level)
def randomForest(trainFeatures, trainResponses, testFeatures, maxFeatures = 'log2', nTree=100):
## Settings of random forests regressor
regModel = RandomForestRegressor(n_estimators=nTree, max_features=maxFeatures)
## Train the random forests regressor
regModel.fit(trainFeatures, trainResponses)
## Prediction
testResponsesPred = regModel.predict(testFeatures)
return testResponsesPred
def evalTrainStationTestStation(trainStation, testStation, features):
trainX, _, trainY, _ = splitDataForXValidation(set([trainStation]), set(), "location", dataByStation[trainStation], features, "target")
_, testX2, _, testY2 = splitDataForXValidation(set(), set([testStation]), "location", dataByStation[testStation], features, "target")
model = RandomForestRegressor(max_depth=10, n_estimators = 60, n_jobs = -1, random_state=42)
model.fit(trainX, trainY)
prediction = model.predict(testX2)
rmse = rmseEval(testY2, prediction)[1]
print("Training on station " + str(trainStation) + ", applying on station " + str(testStation) + ": rmse: " + str(rmse))
return rmse
def RF_Model(Scaled_Input_Data, Output_Data):
T0 = time.time()
n = len(Scaled_Input_Data)
RFModel = RandomForestRegressor()
RFModel.fit(Scaled_Input_Data, Output_Data)
RF_Time = time.time() - T0
print('The computational time of Random Forest Regression for ', n, ' examples is: ', RF_Time)
MSEs_RF = cross_validation.cross_val_score(RFModel, Scaled_Input_Data, Output_Data, cv=cross_validation.LeaveOneOut(n), scoring="mean_absolute_error")
MeanMSE_RF = np.mean(list(MSEs_RF))
print('The average MSE of Random Forest Regression for ', n, ' examples is: ', (-1*MeanMSE_RF))
return(MeanMSE_RF, RFModel)
def run(self):
print "Reading device separations..."
indexes = np.load("indexesTrain.npy")
self.train = self.train.values
print "Getting attributes..."
trainFeatures = [self.getMainFeatures(self.train, indexes, i) for i in range(len(indexes))]
for i in range(len(indexes)):
(trainVect, targetVect) = self.getAttributes(trainFeatures, indexes, i)
classifier = RandomForestRegressor(n_estimators=500, verbose=2, n_jobs=4, random_state=1)
classifier.fit(trainVect, targetVect)
pickle.dump(classifier, open("models/models" + str(i) + ".mod", "w"))
def rf_lc(self, trainX, trainY):
trainY_t = self.target_transform( trainY)
clf = RandomForestRegressor( **self.rf_hyper)
clf.fit( trainX, trainY_t)
(mean_train, mean_test, max_train, max_test) = self.compute_error(clf, trainX, trainY)
print ("mean_train err, mean_test err, followed by max: ", ( mean_train, mean_test, max_train, max_test))
self.log( ( mean_train, mean_test, max_train, max_test))
return (clf, mean_train, mean_test, max_train, max_test)
def train_model(X_train, y_train):
model = RandomForestRegressor(n_estimators=50,
criterion='mse',
max_features='auto',
max_depth=25,
min_samples_split=1e-4,
min_samples_leaf=1e-5,
n_jobs=-1,
verbose=10)
model.fit(X_train, y_train)
return model
def randomForestFeatures(df, X_train, y_train):
"""
INPUT: A dataframe to, X_train, y_train
OUTPUT: A list of tuples ranking the feature importance generated from the
PURPOSE: To identify in a robust easy-to-use way what features are most relevant
"""
names = df.iloc[:,1:-1].columns
rf = RandomForestRegressor()
rf.fit(X_train, y_train)
tups = (sorted(zip(map(lambda x: round(x, 4), rf.feature_importances_), names),
reverse=True))
return tups
def train_model(X_train, y_train):
print("training the model ...")
rf = RandomForestRegressor(n_estimators=500,
max_depth=5,
n_jobs=-1,
verbose=2)
rf.fit(X_train, y_train)
y_pred_train = rf.predict(X_train)
print(".. training RMSE : {:0.3f} %".format(
mean_squared_error(y_train, y_pred_train) * 100))
#print(".. training R2 : {:0.3f} %".format(r2_score(y_train,y_pred_train)*100))
print(".. training MAE : {:0.3f} %".format(
mean_absolute_error(y_train, y_pred_train) * 100))
return rf
def RandomForest(weiboid, x_train, y_train, x_test, y_test, d):
params = {
'n_estimators': 1000,
'max_depth': d,
'min_samples_split': 1,
'warm_start': True,
'oob_score': True
}
clf = RandomForestRegressor(**params)
clf.fit(x_train, y_train)
y_predict = clf.predict(x_test)
r = rmse(y_test, y_predict)
#fig(weiboid,y_test,y_predict)
return y_predict, r
def RandomForest(x_train,y_train,x_test,y_test):
degree = [1,2,3,4,7]
result = {}
rmse_list = []
for d in degree:
params = {'n_estimators': 1000, 'max_depth': d, 'min_samples_split': 1,'warm_start':True}
clf = RandomForestRegressor(**params)
clf.fit(x_train[:, np.newaxis], y_train)
y_predict = clf.predict(x_test[:, np.newaxis])
rmsevalue = rmse(y_test,y_predict)
result[rmsevalue] = [y_predict,d]
rmse_list.append(rmsevalue)
rmseMin = min(rmse_list)
return rmsevalue,result[rmseMin]
def test_overwrite_ensemble_model_invalid(self):
(x_train, y_train), (x_test, y_test) = TestUtil.get_boston_housing()
model_builder = MLPModelBuilder()
explained_model = RandomForestRegressor(n_estimators=64,
max_depth=5,
random_state=1)
explained_model.fit(x_train, y_train)
masking_operation = ZeroMasking()
loss = binary_crossentropy
num_models = 5
explainer = CXPlain(explained_model,
model_builder,
masking_operation,
loss,
num_models=num_models)
file_names = [
CXPlain.get_config_file_name(),
CXPlain.get_explained_model_file_name(".pkl"),
CXPlain.get_loss_pkl_file_name(),
CXPlain.get_model_builder_pkl_file_name(),
CXPlain.get_masking_operation_pkl_file_name()
]
# Test with untrained explanation model.
for file_name in file_names:
tmp_dir = TestExplanationModel.make_at_tmp(file_name)
with self.assertRaises(ValueError):
explainer.save(tmp_dir, overwrite=False)
# Test with trained explanation model.
explainer.fit(x_train, y_train)
file_names = [
CXPlain.get_config_file_name(),
CXPlain.get_explained_model_file_name(".pkl"),
CXPlain.get_loss_pkl_file_name(),
CXPlain.get_model_builder_pkl_file_name(),
CXPlain.get_masking_operation_pkl_file_name()
] + [
CXPlain.get_prediction_model_h5_file_name(i)
for i in range(num_models)
]
for file_name in file_names:
tmp_dir = TestExplanationModel.make_at_tmp(file_name)
with self.assertRaises(ValueError):
explainer.save(tmp_dir, overwrite=False)
def doPrediction(locations, data, columns, features, columns2, outputFileName):
predictionData = {}
for c in columns2:
predictionData[c] = []
# modelling
for location in locations:
trainX, testX, trainY, testY, dataY = splitDataForXValidation(
location, "location", data, features, columns, "target")
print("\tT+W #train: " + str(len(trainY)) + ", #test:" +
str(len(testY)))
model = RandomForestRegressor(min_samples_leaf=2,
n_estimators=650,
n_jobs=-1,
random_state=42)
model.fit(trainX, trainY)
prediction = model.predict(testX)
rmse = rmseEval(testY, prediction)[1]
print("\trmse: " + str(rmse))
for c in columns2:
if c == 'prediction':
predictionData[c].extend(prediction)
else:
predictionData[c].extend(dataY[c])
for c in predictionData:
print("\t" + c + " -> #" + str(len(predictionData[c])))
rmse = rmseEval(predictionData['target'], predictionData['prediction'])[1]
print("overall RMSE: " + str(rmse))
print("Writing out results...")
output = open(outputFileName, 'w')
output.write(','.join([str(x) for x in columns2]))
output.write("\n")
for i in range(0, len(predictionData['target'])):
output.write(str(predictionData[columns2[0]][i]))
for j in range(1, len(columns2)):
output.write(",")
output.write(str(predictionData[columns2[j]][i]))
output.write("\n")
output.close()
print("Done...")
def test_boston_housing_valid(self):
(x_train, y_train), (x_test, y_test) = TestUtil.get_boston_housing()
explained_model = RandomForestRegressor(n_estimators=64,
max_depth=5,
random_state=1)
explained_model.fit(x_train, y_train)
model_builder = MLPModelBuilder(num_layers=2,
num_units=32,
activation="relu",
p_dropout=0.2,
verbose=0,
batch_size=32,
learning_rate=0.001,
num_epochs=3,
early_stopping_patience=128)
masking_operation = ZeroMasking()
loss = mean_squared_error
for num_models in [2, 5, 10]:
explainer = CXPlain(explained_model,
model_builder,
masking_operation,
loss,
num_models=num_models)
explainer.fit(x_train, y_train)
eval_score = explainer.score(x_test, y_test)
train_score = explainer.get_last_fit_score()
median, confidence = explainer.predict(x_test,
confidence_level=0.95)
self.assertTrue(median.shape == x_test.shape)
self.assertTrue(confidence.shape == x_test.shape + (2, ))
# Flatten predictions for iteration below.
median = median.reshape((len(x_test), -1))
confidence = confidence.reshape((len(x_test), -1, 2))
for sample_idx in range(len(x_test)):
for feature_idx in range(len(x_test[sample_idx])):
self.assertTrue(confidence[sample_idx][feature_idx][0] <=
median[sample_idx][feature_idx] <=
confidence[sample_idx][feature_idx][1])
self.assertTrue(
confidence[sample_idx][feature_idx][0] >= 0)
self.assertTrue(
confidence[sample_idx][feature_idx][1] >= 0)
def perform_random_forest_regressor(train_set, train_target, test_set, predictors, estimators=10, depth=None, splits=2):
alg = RandomForestRegressor(random_state=1)
alg.fit(train_set[predictors], train_target)
#importances = alg.feature_importances_
#print("Original ",numpy.argsort(importances))
#indices = numpy.argsort(importances)[::-1]
#print (" importances ",importances)
#print (" indices ",indices)
#for f in range(train_set.shape[1]-2):
# print("%2d) %-*s %f" % (f+1,30,predictors[indices[f]],
# importances[indices[f]]))
predictions = alg.predict(test_set[predictors])
return predictions;
class QuantileForestRegression(absmodel.Module):
def __init__(self, n_estimator=500):
super(QuantileForestRegression, self).__init__()
self.model = RandomForestRegressor(n_estimators=n_estimator)
self.fitted = False
def _fit(self, x, y, verbose=False, load=False):
return self.model.fit(x, y)
def predict(self, x, y, label=None):
d, up = self.pred_ints(model=self.model, x=x)
return d, up
def pred_ints(self, model, x, percentile=95):
err_down = []
err_up = []
for i in range(len(x)):
preds = []
for pred in model.estimators_:
preds.append(pred.predict(x[i])[0])
err_down.append(np.percentile(preds, (100 - percentile) / 2.))
err_up.append(np.percentile(preds, 100 - (100 - percentile) / 2.))
return err_down, err_up
def calcRandomForest(channels_training, channels_testing, target_training,
target_testing):
clf = RandomForestRegressor(n_estimators=500,
max_features=len(channels_training[0]))
clf = clf.fit(channels_training, target_training)
predictions = clf.predict(channels_testing)
comp = [predictions, target_testing]
return clf, comp
def main(train_file='train.csv', test_file='test.csv', output_file='predict.csv'):
print "Loading data..."
train_data = pd.read_csv(train_file)
test_data = pd.read_csv(test_file)
y = np.array(train_data[["ACTION"]])
#X = np.array(train_data.ix[:,1:-1]) # Ignores ACTION, ROLE_CODE
X = np.array(train_data[["RESOURCE","MGR_ID", "ROLE_ROLLUP_1", "ROLE_ROLLUP_2", "ROLE_DEPTNAME", "ROLE_FAMILY_DESC", "ROLE_FAMILY", "ROLE_DEPTNAME", "ROLE_CODE"]])
X_test = np.array(test_data[["RESOURCE","MGR_ID", "ROLE_ROLLUP_1", "ROLE_ROLLUP_2", "ROLE_DEPTNAME", "ROLE_FAMILY_DESC", "ROLE_FAMILY","ROLE_DEPTNAME", "ROLE_CODE"]]) # Ignores ID, ROLE_CODE
SEED = 4
#clf = DecisionTreeClassifier(criterion="entropy").fit(X,y)
clf = RandomForestRegressor(n_estimators=300, min_samples_split=15, min_density=0.1,compute_importances=True).fit(X,y)
print clf.feature_importances_
#Try feature selection
mean_auc = 0.0
n = 10
for i in range(n):
X_train, X_cv, y_train, y_cv = cross_validation.train_test_split(X, y, test_size=.10, random_state=i*SEED)
# if you want to perform feature selection / hyperparameter
# optimization, this is where you want to do it
# train model and make predictions
clf.fit(X_train, y_train)
preds = clf.predict(X_cv)
# compute AUC metric for this CV fold
fpr, tpr, thresholds = metrics.roc_curve(y_cv, preds, pos_label=1)
roc_auc = metrics.auc(fpr, tpr)
print "AUC (fold %d/%d): %f" % (i + 1, n, roc_auc)
mean_auc += roc_auc
print "Mean AUC: %f" % (mean_auc/n)
predictions = clf.predict_(X_test)
#print predictions
#print 'Writing predictions to %s...' % (output_file)
create_test_submission(output_file, predictions)
return 0
def rf(week, timestampWeekCategory, stationNames, ospmData2013, ospmData2014,
data2013, data2014):
columns = []
for c in data2013:
columns.append(c)
columns.remove("location")
columns.remove("timestamp")
columns.remove("target")
X = []
y = []
for i in range(0, len(data2013["target"])):
timestamp = str(int(data2013["timestamp"][i]))
weekC = timestampWeekCategory[timestamp]
if int(weekC) >= week:
y.append(data2013["target"][i])
x = []
for c in columns:
x.append(data2013[c][i])
X.append(x)
model = RandomForestRegressor(min_samples_leaf=9,
n_estimators=59,
n_jobs=-1,
random_state=42)
model.fit(X, y)
# print(str(len(X)))
X = []
y = []
for i in range(0, len(data2014["target"])):
y.append(data2014["target"][i])
x = []
for c in columns:
x.append(data2014[c][i])
X.append(x)
prediction = model.predict(X)
rmse = rmseEval(y, prediction)
return rmse
def run(self):
# extract data from the batch
df_train = pd.read_csv(self.input().path, header=[0, 1])
X, y = preprocess2(df_train, snr=10.)
# train regressor
reg = RandomForestRegressor(10, min_samples_leaf=10, max_depth=9,
n_jobs=-1)
# reg = KNeighborsRegressor(algorithm="auto")
# reg = LinearRegression()
# reg = sklearn.svm.SVR(kernel="rbf", degree=3, C=100., gamma=10.)
# reg = LinearSaO2Unmixing()
reg.fit(X, y.values)
# reg = LinearSaO2Unmixing()
# save regressor
regressor_file = self.output().open('w')
pickle.dump(reg, regressor_file)
regressor_file.close()
def run(self):
# extract data from the batch
df_train = pd.read_csv(self.input().path, header=[0, 1])
X, y = preprocess2(df_train, snr=10.)
# train regressor
reg = RandomForestRegressor(10, min_samples_leaf=10, max_depth=9,
n_jobs=-1)
# reg = KNeighborsRegressor(algorithm="auto")
# reg = LinearRegression()
# reg = sklearn.svm.SVR(kernel="rbf", degree=3, C=100., gamma=10.)
# reg = LinearSaO2Unmixing()
reg.fit(X, y.values)
# reg = LinearSaO2Unmixing()
# save regressor
regressor_file = self.output().open('w')
pickle.dump(reg, regressor_file)
regressor_file.close()
def make_models(self, missing_columns):
available_table = self.full_table.copy()
#clear out the table
for column in missing_columns:
del available_table[column]
available_features = available_table.as_matrix()
clfs = {}
#build a model for each missing column
for column in missing_columns:
labels = self.full_table.as_matrix(columns = [column])
labels = np.reshape(labels, (len(labels))) #unnest the arrays
clf = RandomForestRegressor(n_estimators = 100)
clf.fit(available_features, labels, available_table['WGTP'])
clfs[column] = clf
return clfs
def eval_one(features):
all_predictions = []
all_observations = []
for location in locations:
trainX, testX, trainY, testY = splitDataForXValidation(
location, "location", data, features, "target")
model = RandomForestRegressor(min_samples_leaf=2,
random_state=42,
n_estimators=650,
n_jobs=-1)
model.fit(trainX, trainY)
predictions = model.predict(testX)
all_observations.extend(testY)
all_predictions.extend(predictions)
rmse = rmseEval(all_observations, all_predictions)[1]
log("\tRMSE: " + str(rmse))
def modeltrain(X_train, y_train, X_test, y_test):
from sklearn.ensemble.forest import RandomForestRegressor
# Generando el modelo
RF_Model = RandomForestRegressor(n_estimators=100,max_features=1)
# Ajustando el modelo con X_train y y_train
rgr = RF_Model.fit(X_train, y_train)
y_train_predict = (rgr.predict(X_train)).astype(int)
y_test_predict = (rgr.predict(X_test)).astype(int)
return y_train_predict , y_test_predict , rgr
def test_fmt_sklearn_preds_regression(self):
"""test fmt_sklearn_preds on regression case"""
modelobj_regr = RandomForestRegressor()
model_df =self.df.loc[:, self.df.columns != 'target']
modelobj_regr.fit(model_df,
self.df.loc[:, 'target'])
fmtd_outputs = fmt_model_outputs.fmt_sklearn_preds(getattr(modelobj_regr, 'predict'),
modelobj_regr,
model_df,
self.df,
'target',
'regression')
self.assertIn('predictedYSmooth',
fmtd_outputs.columns.values,
"""fmt_sklearn_preds on regression case does not return predictions""")
def predict_per_cpu_full():
data, target = load_data()
data, target, labels = normalize_data(data, target)
data = data[['C0', 'cpuFull']]
data['target'] = target
split_by_types = dict()
cpu_groups = data.groupby('cpuFull')
for name, group in cpu_groups:
X_train, X_test, y_train, y_test = train_test_split(group['C0'].reshape(-1, 1), group['target'])
split_by_types[str(name)] = {
'train': {
'data': X_train,
'target': y_train
},
'test': {
'data': X_test,
'target': y_test
}
}
# print split_by_types
summ = 0.0
for cpu, data_set in split_by_types.iteritems():
plt.figure()
# reg = SGDRegressor(loss='huber', n_iter=100, alpha=0.0)
reg = RandomForestRegressor(n_estimators=5)
reg.fit(data_set['train']['data'], data_set['train']['target'])
test_data = data_set['test']['data']
y_pred = reg.predict(test_data)
print mape(data_set['test']['target'], y_pred), cpu
plt.scatter(test_data, data_set['test']['target'], s=3, color='g', label='actual')
plt.scatter(test_data, y_pred, s=3, color='r', label='predicted')
plt.legend(loc='upper left')
plt.ylabel('mul time')
plt.title('Category: {}'.format(cpu))
plt.savefig('imgs/{}.png'.format(cpu))
def train(data,val_ind,indices):
max_numb = val_ind.shape[1]
regs = []
for i in range(max_numb):
regs.append(0)
for i in indices:
# print i
# reg = sklearn.linear_model.Lasso(max_iter=3000)
reg = RandomForestRegressor()
# reg=skl.tree.DecisionTreeRegressor()
# reg = skl.linear_model.LinearRegression()
# reg = AdaBoostRegressor()
# print val_ind.shape
# print val_ind[:,i]
# print data.shape
# print data[0]
# print len(val_ind[:,i])
reg.fit(data,val_ind[:,i])
regs[i]=reg
return regs
import pandas as pd
from sklearn.ensemble.forest import RandomForestRegressor
import time
dset = pd.read_csv("./data/concrete_data.csv")
X = dset.iloc[:, 0:7]
y = dset.iloc[:, 8]
estimator = RandomForestRegressor(max_features = 3, n_estimators = 50, n_jobs = 1, oob_score = True)
t0 = time.time()
estimator.fit(X, y)
print(time.time() - t0)
# fit a linear model with no bells and whistles
model = linear_model.LinearRegression()
model.fit(train_X, train_Y)
# look at the r squared on the training data and the test data
model.score(train_X, train_Y)
model.score(test_X, test_Y)
# See if I can get the r squared on the test data lower by using more complex models
# random forest
forest = RandomForestRegressor()
# fit the data without using cross val to select parameters
# note that train score is much higher than test score
forest.fit(train_X, train_Y)
forest.score(train_X, train_Y)
forest.score(test_X, test_Y)
# fit a random forest regressor using grid search to
# select the number of trees and max depth
new_forest = RandomForestRegressor()
params_grid = [{'max_depth': [3, 5,10, None], 'n_estimators': [5,10,15,20, 50, 80]} ]
grid_search = GridSearchCV(new_forest, params_grid, cv=10)
grid_search.fit(train_X, train_Y)
grid_search.score(test_X, test_Y)
grid_search.best_estimator_
# fit a boosted regression
boost = GradientBoostingRegressor()
# Look at scatter plot of OTU abundance vs. age to visualize the correlation
fig, ax= plt.subplots()
ax.scatter(x, y)
ax.set_xlabel('OTU #' + otu)
ax.set_ylabel('Age')
ax.text(0.01,0.95, r'$\rho$ = {:.2f}'.format(r), transform=ax.transAxes)
#%% 3. Build a Random Forest Regressor
## 3.1 Build the regressor
rfreg = RandomForestRegressor(n_estimators=1000, oob_score=True)
# We aren't classifying samples here, so we can just use the whole OTU table to build our regression
X = data.abun_df.values
Y = [float(data.meta_df.loc[smpl, 'BMI']) for smpl in data.abun_df.index]
rfreg = rfreg.fit(X,Y)
## 3.1.1 Look at true vs. predicted values from out of bag estimations
fig, ax = plt.subplots()
ax.scatter(Y, rfreg.oob_prediction_)
ax.set_xlabel('True')
ax.set_ylabel('Predicted')
ax.set_title('RF regression on BMI')
## 3.2 Look at the important features in the regression by inspecting their coefficient weights
feats = pd.DataFrame(index=data.abun_df.columns, columns=['importance'], data=rfreg.feature_importances_)
feats = feats.sort(columns='importance', ascending=False)
feats['normalized_importance'] = feats['importance']/max(feats['importance'])
# Look at the top 5 features and their importance. Each row name is the OTU ID
feats.head(5)
# Initiate the monthly trade object
monthData = trade_model.monthlyModel(1, 2009, 6, 2013, 6, 2012, 6, 2013)
# Download data from Yahoo finance
monthData.monthlyDataDownload()
# Pre-processing of training an testing data
monthData.trainFeaturePre()
# Read pre-processed data from hard drive
# monthData.trainFeaturePreHd()
# Number of training months
trainSpan = len(monthData.xTrain[:,0,0]) - monthData.testSpan
# Initiate a random forest regressor
clf = RandomForestRegressor(n_estimators=10)
#
totalReturn = 1
predictedReturn = np.zeros(monthData.stockNum)
monthlyReturn = np.zeros(monthData.testSpan)
aggReturn = np.zeros(monthData.testSpan+1)
aggReturn[0] = 1
# rolling training and testing
for j in range(0, monthData.testSpan):
for i in range(0, monthData.stockNum):
clf.fit(monthData.xTrain[j:trainSpan+j, :, i], monthData.yTrain[j:trainSpan+j, 0, i])
predictedReturn[i] = clf.predict(monthData.xTest[j, :, i])
monthlyReturn[j] = monthData.por10Returns(j, predictedReturn)
yearReturn = totalReturn * (monthlyReturn[j]+1)
aggReturn[j+1] = aggReturn[j]*(1+monthlyReturn[j])
print monthlyReturn
print 'overall:', totalReturn
sp.portfolioVSspy(6, 2012, 6, 2013, aggReturn[1:])
nucleus = 'N' # make command line option; supported nuclei are ['H','N','CA','HA','CB','C']
# Generate training and test set
X_train,y_train = OrganizeData(nucleus, 'train')
X_test, y_test = OrganizeData(nucleus, 'test')
# Feature scaling
X_train_scaled = preprocessing.scale(X_train)
X_test_scaled = preprocessing.scale(X_test)
# Set the parameters for the random forest estimator
estimator = RandomForestRegressor(n_estimators=50, max_features=16, max_depth=25,
min_samples_split=5, min_samples_leaf=5, random_state=0)
# Build the random forest of regression trees from the training set
estimator = estimator.fit(X_train_scaled,y_train)
print estimator.score(X_train_scaled,y_train)
print estimator.score(X_test_scaled,y_test)
# Predict regression target for the test set
predicted = estimator.predict(X_train_scaled)
cc = np.corrcoef(y_train,predicted)
print cc
print estimator
#my_plotting.simple_plot_overlay(y_train,predicted)
predicted = estimator.predict(X_test_scaled)
cc = np.corrcoef(y_test,predicted)
print cc
print estimator
def fit(self, X, y, sample_weight=None):
sample_weight = normalize_weight(y, sample_weight, sig_weight=self.sig_weight, pow_sig=self.pow_sig,
pow_bg=self.pow_bg)
target = sample_weight + self.gap
target[y == 0] *= -1
RandomForestRegressor.fit(self, X, y, sample_weight=sample_weight)
newtrain = pd.DataFrame(newtrain, columns = cols)
newtest = pd.DataFrame(newtest, columns = cols)
#test = test.join(pd.DataFrame(test.Date.apply(splitTime).tolist(), columns = ['year','mon','day']))
#newtest = test.drop('StateHoliday',1).join(pd.get_dummies(test['StateHoliday']).rename(columns=lambda x: 'StateHoliday' +"_"+str(x)))
#newtest = pd.merge(newtest,store, on="Store")
#newtest.drop(['Date'],axis = 1,inplace=True)
#assert(np.sum(newtrain.var()==0)==0)
#
#toDrop = list(set(newtrain.columns.values)-set(newtest.columns.values) )
features = [col for col in newtrain.columns if col not in ['Customers', 'Sales', 'Date','LogSale','datetimes']]
#
rf = RandomForestRegressor(n_estimators=100)
print('Starting training...')
rf.fit(newtrain[features].fillna(-1),newtrain.LogSale)
print('Predicting train values...')
newtrain['mypred'] = rf.predict(newtrain[features].fillna(-1))
newtrain['mypred'] = np.exp(newtrain['mypred'])-1
train_error = rmspe(newtrain[newtrain.Sales>0].Sales,newtrain[newtrain.Sales>0].mypred)
print('train set error',train_error)
newtest['mypred'] = rf.predict(newtest[features].fillna(-1))
newtest['mypred'] = np.exp(newtest['mypred'])-1
test_error = rmspe(newtest[newtest.Sales>0].Sales,newtest[newtest.Sales>0].mypred)
print('test set error',test_error)
train_results.append(train_error)
test_results.append(test_error)
print('mean train error', np.mean(train_results))
print('mean test error',np.mean(test_results))
all_data_valid, all_targets_valid = generate_array(hdulist_valid,
feature_index,
target_index)
clf_adaboost = AdaBoostRegressor(DecisionTreeRegressor(max_depth=8), n_estimators=50,
loss='linear', random_state=0)
clf_extra_trees = ExtraTreesRegressor(n_estimators=8, random_state=0, max_depth=30)
clf_random_forest = RandomForestRegressor(n_estimators=8, random_state=0, max_depth=30)
clf_adaboost.fit(all_data_test.T, all_targets_test[0])
predicted = clf_adaboost.predict(all_data_valid.T)
clf_extra_trees.fit(all_data_test.T, all_targets_test[0])
predicted_extra = clf_extra_trees.predict(all_data_valid.T)
clf_random_forest.fit(all_data_test.T, all_targets_test[0])
predicted_forest = clf_random_forest.predict(all_data_valid.T)
delta_ada = all_targets_valid[0] - predicted
delta_extra = all_targets_valid[0] - predicted_extra
delta_forest = all_targets_valid[0] - predicted_forest
std_ada = get_standart_deviation(delta_ada)
std_extra = get_standart_deviation(delta_extra)
std_forest = get_standart_deviation(delta_forest)
plt.hist(delta_ada, bins=150, color='g', label='Adaboost '+str(np.round(std_ada,4)))
plt.hist(delta_extra, bins=150, color='b', label='Extra_Trees '+str(np.round(std_extra,4)))
plt.hist(delta_forest, bins=150, color='r', label='Random_Forest '+str(np.round(std_forest,4)))
title = "Compare adaboost, extra_tree and Random_Forests"
plt.title(title)
predictions3 = []
predictions4 = []
offset = int(0.7 * len(X))
for i in range(10):
X, y = shuffle(boston.data, boston.target)
X_train, y_train = X[:offset], y[:offset]
X_test, y_test = X[offset:], y[offset:]
regressor = GradientBoostingRegressor(max_depth=20, n_estimators=140)
regressor2 = DecisionTreeRegressor(max_depth=6)
regressor3 = LinearRegression()
regressor4 = RandomForestRegressor()
regressor.fit(X_train, y_train)
regressor2.fit(X_train, y_train)
regressor3.fit(X_train, y_train)
regressor4.fit(X_train, y_train)
y_pred = regressor.predict(x)
y_pred2 = regressor2.predict(x)
y_pred3 = regressor3.predict(x)
y_pred4 = regressor4.predict(x)
predictions.append(y_pred)
predictions2.append(y_pred2)
predictions3.append(y_pred3)
predictions4.append(y_pred4)
print "\nPrediction = " + str(y_pred)
print "Prediction = " + str(y_pred2)
print "Prediction = " + str(y_pred3)
print "Prediction = " + str(y_pred4)
print '\n'
print 'Boosting max', np.max(predictions), 'min', np.min(predictions), 'variance', np.max(predictions) - np.min(predictions)
class ItemSetModel(object):
"""docstring for ItemSetModel"""
clf = None
MODEL_PATH = os.path.join(settings.BASE_DIR, 'set_analyzer', 'analysis', 'models')
CACHE_FILE = os.path.join(MODEL_PATH, 'model_cache.cache')
def __init__(self):
super(ItemSetModel, self).__init__()
#self.clf = DecisionTreeRegressor()
#self.clf = Lasso(0.1)
#self.clf = SVR(kernel='rbf')
#self.clf = ElasticNetCV()
self.clf = RandomForestRegressor(max_depth=7, n_estimators=10)
def get_data_sets(self, num_matches, cache=False, **kwargs):
"""
Data Schema:
Input:
1 My champion ID
6 My Champion's class info
6 [Other team's cumulative class info]
7 [7 Final Items]
5 [first 5 items purchased]
________________________________________
25 features
Output:
Score = A(Gold/time) + B(xp/time) + C(win)
________________________________________
1 Output
"""
#Presize data
features = 25
num_participants = num_matches*10
input_data = np.zeros((num_participants, features))
output_data = np.zeros(num_participants)
row_num = 0
get_champ_id = lambda x : x.champion.champion_id
diff_team = lambda x , y : x.team_id != y.team_id
item_purchased = lambda x: x.event_type == "ITEM_PURCHASED"
#Iterate over every match in the database
for match in Match.objects(**kwargs)[:num_matches]:
#Prepare users and teams
team_map = {}
team_data = np.zeros((2,6)) #Store the sum of each team's tags
count = 0
for tag in match.teams:
team_map[int(tag)] = count
count+=1
#Prepare champion class data
for p in match.participants.values():
for tag in p.champion.tags:
team_data[team_map[p.team_id], :] += np.array(p.champion.class_data)
#Iterate over every user in the match
for pid, participant in match.participants.items():
col_num = 0
#My Champion's info
input_data[row_num][col_num] = get_champ_id(participant)
col_num+=1
input_data[row_num][col_num:col_num+6] = np.array(participant.champion.class_data)
col_num+=6
#Other Team's champion attributes
if(team_map[participant.team_id] == 0):
input_data[row_num][col_num:col_num+6] = team_data[1,:]
else:
input_data[row_num][col_num:col_num+6] = team_data[0,:]
col_num+=6
#My items
for item_id in participant.final_build:
input_data[row_num][col_num] = item_id
col_num+=1
#My Item purchases
count = 0
for item_purchase in (x for x in participant.item_events if item_purchased(x)):
if(count==5):
break
input_data[row_num][col_num] = item_purchase.payload['itemId']
col_num += 1
count += 1
#Score
# Assume that average gold/sec is ~8
# Assume that average kda is ~2.6
# Have a game win worth some bonus
score = participant.kda()*3 + participant.gold_earned/match.duration + (4 if match.teams[str(participant.team_id)].won else 0)
output_data[row_num] = score
row_num+=1
if(cache):
print('Caching data...')
self.cache_data((input_data, output_data))
return (input_data, output_data)
def cache_data(self, data):
with open(self.CACHE_FILE, 'wb') as f:
pickle.dump(data, f)
def get_cached_data(self, num_rows):
with open(self.CACHE_FILE, 'rb') as f:
return pickle.load(f)[:num_rows]
def train(self, X, Y, train_ratio=1, **kwargs):
print("Training model...")
if(train_ratio==1):
print("Using {} rows".format(len(X)))
self.clf.fit(X,Y)
else:
n = len(X)
tn = int(n*train_ratio)
print("Using {} rows".format(tn))
self.clf.fit(X[:tn,:],Y[:tn])
print("Evaluating model...")
evaluate_fit(self.clf, X[tn:,:],Y[tn:])
def predict(self, X):
return self.clf.predict(X)
#MODEL EVAUATION
def k_fold(self, folds, **kwargs):
X, Y = self.get_data_sets(**kwargs)
k_fold_evaluate(self.clf, X, y, folds)
#LOAD AND SAVE
def save(self, filename):
dirname = os.path.join(self.MODEL_PATH, filename)
if(not os.path.exists(dirname)):
os.makedirs(dirname)
else: #Empty folder
for file in os.listdir(dirname):
file_path = os.path.join(dirname, file)
if os.path.isfile(file_path):
os.unlink(file_path)
path = os.path.join(dirname, "{}.pkl".format(filename))
joblib.dump(self.clf, path)
def load(self, filename):
path = os.path.join(self.MODEL_PATH, filename, "{}.pkl".format(filename))
self.clf = joblib.load(path)
store = store.drop("Assortment", 1).join(
pd.get_dummies(store["Assortment"]).rename(columns=lambda x: "Assortment" + "_" + str(x))
)
train["StateHoliday"] = [mychange(x) for x in train.StateHoliday]
test["StateHoliday"] = [mychange(x) for x in test.StateHoliday]
train = train.drop("StateHoliday", 1).join(
pd.get_dummies(train["StateHoliday"]).rename(columns=lambda x: "StateHoliday" + "_" + str(x))
)
test = test.drop("StateHoliday", 1).join(
pd.get_dummies(test["StateHoliday"]).rename(columns=lambda x: "StateHoliday" + "_" + str(x))
)
train = pd.merge(train, store, on="Store")
test = pd.merge(test, store, on="Store")
repeat = 1
print("Splitting data...")
for i in range(repeat):
features = [col for col in test.columns if col not in ["Customers", "Sales", "Date", "LogSale", "datetimes", "Id"]]
rf = RandomForestRegressor(n_estimators=100)
print("Starting training...")
rf.fit(train[features].fillna(-1), train.LogSale)
test["mypred"] = rf.predict(test[features].fillna(-1))
test["mypred"] = np.exp(test["mypred"]) - 1
test["Sales"] = test.mypred
test[["Id", "Sales"]].to_csv("rand_for_kag_v4-9.csv", index=False)
def ts_rf(n,fea,step,ntrees,njobs):
#Random Forest Model for time series prediction
#from sklearn import svm
import math
from sklearn import metrics
import matplotlib.pyplot as plt
from scipy.linalg import hankel
import numpy as np
from sklearn.ensemble.forest import RandomForestRegressor
#input data from csv file
#use n datapoints
#n=1100
# # of features of training set
## fre=50
# # how many steps to predict
#step=29
#fea=50
path='/Users/royyang/Desktop/time_series_forecasting/csv_files/coffee_ls.txt'
path1 = '/Users/royyang/Desktop/time_series_forecasting/csv_files/coffee_ls_nor.txt'
result_tem=[]
date = []
with open(path) as f:
next(f)
for line in f:
item=line.replace('\n','').split(' ')
result_tem.append(float(item[1]))
date.append(item[2])
mean = np.mean(result_tem)
sd = np.std(result_tem)
result=(result_tem-mean)/sd
#form hankel matrix
X=hankel(result[0:-fea-step+1], result[-1-fea:-1])
y=result[fea+step-1:]
#split data into training and testing
Xtrain=X[:n]
ytrain=y[:n]
Xtest=X[n:]
ytest=y[n:]
# random forest
rf = RandomForestRegressor(n_estimators = ntrees, n_jobs=njobs)
rf_pred = rf.fit(Xtrain, ytrain).predict(Xtest)
#a = rf.transform(Xtrain,'median')
#plot results
LABELS = [x[-6:] for x in date[n+fea+step-1:n+fea+step-1+len(ytest)]]
t=range(n,n+len(ytest))
# plt.show()
# plt.plot(t,y_lin1,'r--',t,ytest,'b^-')
# plt.plot(t,y_lin2,'g--',t,ytest,'b^-')
ypred = rf_pred*sd+mean
ytest = ytest*sd+mean
line1, = plt.plot(t,ypred,'r*-')
plt.xticks(t, LABELS)
line2, = plt.plot(t,ytest,'b*-')
# plt.xlim([500,510])
plt.legend([line1, line2], ["Predicted", "Actual"], loc=2)
#plt.show()
#plt.plot(xrange(n),result[0:n],'r--',t,y_lin3,'b--',t,ytest,'r--')
y_true = ytest
y_pred = ypred
metrics_result = {'rf_MAE':metrics.mean_absolute_error(y_true, y_pred),'rf_MSE':metrics.mean_squared_error(y_true, y_pred),
'rf_MAPE':np.mean(np.abs((y_true - y_pred) / y_true)) * 100}
print metrics_result
def train(training, k):
model = RandomForestRegressor(n_estimators=k, n_jobs=-1)
model.fit(training[:,:-1], training[:,-1])
return model
import json
household = pd.read_csv("../household_complete_one_hot.csv")
if 'KWH' in household.columns:
del household['KWH']
X_columns = [column for column in household.columns if column != "ELEP"]
X = household.as_matrix(columns = X_columns)
y = [label[0] for label in household.as_matrix(columns = ["ELEP"])]
#print(y)
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size = 0.25)
clf = RandomForestRegressor(n_estimators = 100, n_jobs = 8)
clf.fit(X_train, y_train)
print(y_test[:100])
print(metrics.mean_squared_error(clf.predict(X_test), y_test))
print(metrics.r2_score(y_test, clf.predict(X_test)))
features = sorted(zip(X_columns, clf.feature_importances_), key = lambda x : x[1], reverse = True)
print("Features", features)
#fill spaces in ELEP
normalized_pums = pd.read_csv("../joined_weather.csv", delimiter = ',')
print('pums shape', normalized_pums.shape)
with open("../vectorized_puma_regions/puma_list.json") as f:
puma_mapping = json.load(f)
auto = auto_mapper.fit_transform(auto_df)
store_pkl(auto_mapper, "Auto.pkl")
auto_X = auto[:, 0:7]
auto_y = auto[:, 7]
print(auto_X.dtype, auto_y.dtype)
def predict_auto(regressor):
mpg = DataFrame(regressor.predict(auto_X), columns = ["mpg"])
return mpg
auto_tree = DecisionTreeRegressor(random_state = 13, min_samples_leaf = 5)
auto_tree.fit(auto_X, auto_y)
store_pkl(auto_tree, "DecisionTreeAuto.pkl")
store_csv(predict_auto(auto_tree), "DecisionTreeAuto.csv")
auto_forest = RandomForestRegressor(random_state = 13, min_samples_leaf = 5)
auto_forest.fit(auto_X, auto_y)
store_pkl(auto_forest, "RandomForestAuto.pkl")
store_csv(predict_auto(auto_forest), "RandomForestAuto.csv")
auto_regression = LinearRegression()
auto_regression.fit(auto_X, auto_y)
store_pkl(auto_regression, "RegressionAuto.pkl")
store_csv(predict_auto(auto_regression), "RegressionAuto.csv")
train['LogSale'] = np.log(train.Sales+1)
train=pd.merge(train, store, on="Store")
test = pd.merge(test, store, on="Store")
processdata(train)
processdata(test)
repeat = 1
#print('Splitting data...')
for i in range(repeat):
features = [col for col in test.columns if col not in ['Customers', 'Sales', 'Date','LogSale','datetimes','Id']] ##!!!for submission should be test.columns!!!
# features = ['Store', 'CompetitionDistance', 'CompetitionOpenSinceMonth', 'CompetitionOpenSinceYear', 'Promo', 'Promo2',\
# 'Promo2SinceWeek', 'Promo2SinceYear', 'SchoolHoliday', 'DayOfWeek', 'mon', 'day', 'year', 'StoreType', 'Assortment']
# ^^ features taken from xgb model on Kaggle
rf = RandomForestRegressor(n_estimators=100)
print('Starting training...')
rf.fit(train[features],train.LogSale)
# train['mypred'] = rf.predict(train[features])
# train['mypred'] = np.expm1(train.mypred)
# train_error = rmspe(train[train.Sales>0].Sales,train[train.Sales>0].mypred)
# print(train_error)
test['mypred'] = rf.predict(test[features])
test['mypred'] = np.exp(test['mypred'])-1
test['Sales'] = test.mypred
test[[ 'Id', 'Sales' ]].to_csv('rand_for_kag_v4-8.csv', index = False )
def train_random_forest(X, Y):
rf = RandomForestRegressor(n_estimators=20)
rf.fit(X, Y)
return rf
# In[11]: print 'Train Random Forests!' from sklearn.ensemble.forest import RandomForestRegressor RF = RandomForestRegressor(n_estimators = 500, random_state = 0) # In[12]: Rows = np.random.choice(Train.index.values, 400000) Sampled_Train = Train.ix[Rows] Sample_Train_Target = Train_Target.ix[Rows] # RF.fit(Sampled_Train, Sample_Train_Target) RF.fit(Train, Train_Target) # In[ ]: print 'Predict!' Test_Predict = RF.predict(Test.as_matrix()) # In[ ]: print Test_Predict.shape # In[ ]:
clf.fit(X, y)
clf.predict(z)
#########################
from sklearn.ensemble.forest import RandomForestRegressor
regressor = RandomForestRegressor()
parameters = [{"n_estimators": [250, 500, 1000,2000]}]
# Returns the best configuration for a model using crosvalidation
# and grid search
import time
regressor = RandomForestRegressor(n_estimators=300, min_samples_split=1,max_features=67)
regressor.fit(train_np,energy)
pred=regressor.predict(test_np)
print explained_variance_score(energy_test,pred)
print mean_squared_error(energy_test,pred)
r2_score(energy_test,pred)
##prediction comparison
comp = pd.read_csv("H:/bee-efficiency/cisco presentation/pred.csv")
def _2011x2011_ (data_path):
##### LOADING #####
sys.stdout.write("Loading data... ")
# Load data from .csv file
with open(data_path+'_X.csv') as data_file:
reader = csv.reader(data_file)
# Initialize lists for data and class labels
data =[]
# skip header
next(reader, None)
# For each row of the csv file
for row in reader:
data.append([float(x) for x in row])
with open(data_path+'_y.csv') as labels_file:
reader = csv.reader(labels_file)
# Initialize lists for data and class labels
val_ind =[]
# skip header
next(reader, None)
# For each row of the csv file
for row in reader:
val_ind.append(row)
sys.stdout.write("done\n")
##### TRAINING #####
# splitting
data_train, data_test, val_ind_train, val_ind_test \
= skl.cross_validation.train_test_split(data, val_ind, test_size=0.4, random_state=42)
# Cutting date/ ASS/ number value from labels
date_train = [x[0] for x in val_ind_train]
# ASS_train = [x[1] for x in val_ind_train]
val_train = [float(x[1]) for x in val_ind_train]
date_test = [x[0] for x in val_ind_test]
# ASS_test = [x[1] for x in val_ind_test]
val_test = [float(x[1]) for x in val_ind_test]
sys.stdout.write("Training regressor... ")
reg = RandomForestRegressor()
# reg = skl.tree.DecisionTreeRegressor()
# reg = skl.linear_model.LinearRegression()
reg.fit(data_train, val_train)
sys.stdout.write("done\n")
##### PREDICTION #####
sys.stdout.write("Predicting... ")
val_predicted = reg.predict(data_test)
sys.stdout.write("done\n")
##### ERROR #####
df = pd.DataFrame()
df['date'] = pd.to_datetime(date_test)
# df['ASS'] = ASS_test
df['original'] = val_test
df['predicted'] = val_predicted.tolist()
df = df.set_index('date')
# df = df.loc[df['ASS'] == 'CAT'] # one example
df.info()
df.plot()
plt.show()
print "MSE : " + str(mean_squared_error(val_test,val_predicted.tolist()))
