def distribution_test(df: pd.DataFrame = pd.DataFrame()):
if df.empty:
df = filter(read())
distribution.test_exp(df)
distribution.test_gam(df)
distribution.test_wei(df)
distribution.test_logn(df)
distribution.test_pare(df)
def population_statistics(feature_description, data, treatment, target,
threshold, is_above, statistic_functions):
"""
prints the results of the statistics functions on the target parameter based on a split of the data.
the split is based on whether the treatment line in the data is higher then the threshold.
note: filter_by_feature has been defined as filter,
and print details has been defined as print_dt to reduce line length.
:param feature_description: title
:param data: the data for analysis
:param treatment: the field to sort the data by threshold
:param target: the field to be used for the statistic functions
:param threshold: the threshold for sorting the data on treatment by
:param is_above: decides if the data used is above threshold or not
:param statistic_functions: the functions to analise the filtered target data by
:return:
"""
print_dt(
filter(data, treatment,
[x for x in data[treatment] if (x <= threshold) ^ is_above])[0],
target, statistic_functions)
import numpy as np
from models import GP3DModel, IRISplineModel, HybridModel, LogSpaceModel, LinearModel, ProductModel, DifferenceModel
from plot import Plot
import statsmodels.api as sm
from statsmodels.tools import add_constant
metric = sys.argv[1]
nowtime = None
if len(sys.argv) > 2:
nowtime = dateutil.parser.parse(sys.argv[2])
else:
nowtime = dt.datetime.now(timezone.utc)
df = data.get_data()
df = data.filter(df,
max_age=dt.datetime.now() - dt.timedelta(minutes=60),
required_metrics=[metric],
min_confidence=0.01)
irimodel = IRISplineModel("/iri.latest")
irimodel.train(metric)
irimodel_orig = irimodel
if len(df) == 0:
model = irimodel
else:
pred = irimodel.predict(df['station.longitude'].values,
df['station.latitude'].values)
error = pred - df[metric].values
print(df[metric].values)
print(pred)
def main():
df = normalize(filter(read()))
print('Running normality tests...')
normality_test(df)
print('Running distribution tests...')
distribution_test(df)
def normality_test(df: pd.DataFrame = pd.DataFrame()):
if df.empty:
df = filter(read())
normality.test_and(df)
normality.test_ks(df)
normality.test_sh(df)
if event.type == pygame.QUIT:
running = False
if event.type == pygame.KEYDOWN:
if event.key == pygame.K_q:
running = False
#if event.key == pygame.K_LEFT:
# engine.keyEvent = "L"
#if event.key == pygame.K_RIGHT:
# engine.keyEvent = "R"
if event.key == pygame.K_SPACE:
pause = (not pause)
engine.keyEvent = "SPACE"
wave = filter(2)
prediction = Classifier(wave)[-1]
#prediction = predict([wave])
if prediction == "L":
engine.keyEvent = "L"
elif prediction == "R":
engine.keyEvent = "R"
display.fill([0, 0, 0])
if pause:
engine.draw(display)
engine.drawPause(display)
pygame.display.update()