def test_03_predict(self):
"""
ensure log file is created
"""
log_file = os.path.join("logs", "predict-test.log")
if os.path.exists(log_file):
os.remove(log_file)
## update the log
country = 'all'
y_pred = [0]
y_proba = [0.6, 0.4]
runtime = "00:00:02"
model_version = 0.1
target_date = '2021-04-19'
query = {'feature': [0]}
update_predict_log(country,
y_pred,
y_proba,
query,
target_date,
runtime,
model_version,
test=True)
self.assertTrue(os.path.exists(log_file))
def test_04_predict(self):
"""
ensure that content can be retrieved from log file
"""
log_file = os.path.join("logs", "predict-test.log")
## update the log
country = 'all'
y_pred = [0]
y_proba = [0.6, 0.4]
runtime = "00:00:02"
model_version = 0.1
target_date = '2021-04-19'
query = {'feature': [0]}
update_predict_log(country,
y_pred,
y_proba,
query,
target_date,
runtime,
model_version,
test=True)
df = pd.read_csv(log_file)
logged_y_pred = [literal_eval(i) for i in df['y_pred'].copy()][-1]
self.assertEqual(y_pred, logged_y_pred)
def test_01_create_pred_log(self):
"""
test that predict log is created
"""
logfile = the_testlogname("pred")
if os.path.exists(logfile):
os.remove(logfile)
update_predict_log([0], [0, 0, 0], np.array([6.1, 2.8]), MODEL_VERSION,
0.05, True)
self.assertTrue(os.path.exists(logfile))
def model_predict(query, model=None, test=False):
"""
example funtion to predict from model
"""
## start timer for runtime
time_start = time.time()
## input checks
if isinstance(query, dict):
query = pd.DataFrame(query)
elif isinstance(query, pd.DataFrame):
pass
else:
raise Exception("ERROR (model_predict) - invalid input. {} was given".format(type(query)))
## features check
features = sorted(query.columns.tolist())
if features != ['petal_length', 'petal_width', 'sepal_length', 'sepal_width', ]:
print("query features: {}".format(",".join(features)))
raise Exception("ERROR (model_predict) - invalid features present")
## load model if needed
if not model:
model = model_load()
## output checking
if len(query.shape) == 1:
query = query.reshape(1, -1)
## make prediction and gather data for log entry
y_pred = model.predict(query)
y_proba = 'None'
m, s = divmod(time.time()-time_start, 60)
h, m = divmod(m, 60)
runtime = "%03d:%02d:%02d"%(h, m, s)
## update the log file
for i in range(query.shape[0]):
update_predict_log(y_pred[i], y_proba, query.iloc[i].values.tolist(),
runtime, MODEL_VERSION, test=test)
return({'y_pred':y_pred, 'y_proba':y_proba})
def test_04_check_n_preds(self):
"""
test n predictions add n log lines
"""
n = 5
logfile = the_testlogname("pred")
if not os.path.exists(logfile):
before = 0
else:
df = pd.read_csv(logfile, delimiter=',', quotechar='|')
before = df.shape[0]
for i in range(n):
update_predict_log([0], [0, 0, 0], np.array([6.1, 2.8]),
MODEL_VERSION, 0.05, True)
df = pd.read_csv(logfile, delimiter=',', quotechar='|')
after = df.shape[0]
self.assertEqual(n, after - before)
def test_04_predict(self):
"""
ensure that content can be retrieved from log file
"""
log_file = os.path.join("logs", "model_predict", "predict-test.log")
## update the log
y_pred = [0]
y_proba = [0.6, 0.4]
runtime = "00:00:02"
model_version = 0.1
query = ['united_states', 24, 'aavail_basic', 8]
update_predict_log(y_pred,
y_proba,
query,
runtime,
model_version,
test=True)
df = pd.read_csv(log_file)
logged_y_pred = [literal_eval(i) for i in df['y_pred'].copy()][-1]
self.assertEqual(y_pred, logged_y_pred)
def test_03_predict(self):
"""
ensure log file is created
"""
log_file = os.path.join("logs", "model_predict", "predict-test.log")
if os.path.exists(log_file):
os.remove(log_file)
## update the log
y_pred = [0]
y_proba = [0.6, 0.4]
runtime = "00:00:02"
model_version = 0.1
query = ['united_states', 24, 'aavail_basic', 8]
update_predict_log(y_pred,
y_proba,
query,
runtime,
model_version,
test=True)
self.assertTrue(os.path.exists(log_file))
def model_predict(country, year, month, day, all_models=None, test=False):
"""
example funtion to predict from model
"""
## start timer for runtime
time_start = time.time()
## load model if needed
if not all_models:
all_data, all_models = model_load(training=False)
## input checks
if country not in all_models.keys():
raise Exception(
"ERROR (model_predict) - model for country '{}' could not be found"
.format(country))
for d in [year, month, day]:
if re.search("\D", d):
raise Exception(
"ERROR (model_predict) - invalid year, month or day")
## load data
model = all_models[country]
data = all_data[country]
## check date
target_date = "{}-{}-{}".format(year,
str(month).zfill(2),
str(day).zfill(2))
print(target_date)
if target_date not in data['dates']:
raise Exception(
"ERROR (model_predict) - date {} not in range {}-{}".format(
target_date, data['dates'][0], data['dates'][-1]))
date_indx = np.where(data['dates'] == target_date)[0][0]
query = data['X'].iloc[[date_indx]]
## sainty check
if data['dates'].shape[0] != data['X'].shape[0]:
raise Exception("ERROR (model_predict) - dimensions mismatch")
## make prediction and gather data for log entry
y_pred = model.predict(query)
y_proba = None
if 'predict_proba' in dir(model) and 'probability' in dir(model):
if model.probability == True:
y_proba = model.predict_proba(query)
m, s = divmod(time.time() - time_start, 60)
h, m = divmod(m, 60)
runtime = "%03d:%02d:%02d" % (h, m, s)
## update predict log
update_predict_log(country,
y_pred,
y_proba,
query.to_dict(),
target_date,
runtime,
MODEL_VERSION,
test=test)
return ({'y_pred': y_pred, 'y_proba': y_proba})