async def accuracy(self, sources: SourcesContext) -> Accuracy:
# Load saved regression line
regression_line = self.storage.get("regression_line", None)
# Ensure the model has been trained before we try to make a prediction
if regression_line is None:
raise ModelNotTrained("Train model before assessing for accuracy")
# Split regression line tuple into variables, ignore accuracy from
# training data since we'll be re-calculating it for the test data
m, b, _accuracy = regression_line
# X and Y data
x = []
y = []
# Go through all records that have the feature we're testing on and the
# feature we want to predict.
async for record in sources.with_features(
[self.config.feature.name, self.config.predict.name]):
x.append(record.feature(self.config.feature.name))
y.append(record.feature(self.config.predict.name))
# Use self.logger to report how many records are being used for testing
self.logger.debug("Number of test records: %d", len(x))
# Calculate the regression line for test data and accuracy of line
regression_line = [m * x_element + b for x_element in x]
accuracy = coeff_of_deter(y, regression_line)
# Update the accuracy to be the accuracy when assessed on the test data
self.storage["regression_line"] = m, b, accuracy
return Accuracy(accuracy)
async def train(self, sources: SourcesContext) -> None:
# Number of features
nof = len(self.features)
# X and Y data
X = []
Y = []
# Go through all records that have the feature we're training on and the
# feature we want to predict.
async for record in sources.with_features(
self.features + [self.parent.config.predict.name]):
record_data = []
for feature in record.features(self.features).values():
record_data.extend(
[feature] if np.isscalar(feature) else feature)
X.append(record_data)
Y.append(record.feature(self.parent.config.predict.name))
k = self.parent.config.k
X1, Xval = split(X, k)
X = X1
Y1, Yval = split(Y, k)
Y = Y1
X = np.reshape(X, (len(X), nof))
Xval = np.reshape(Xval, (len(Xval), nof))
Y = np.reshape(Y, (len(Y), 1))
Yval = np.reshape(Yval, (len(Yval), 1))
# Use self.logger to report how many records are being used for training
self.logger.debug("Number of training records: %d", len(X))
self.logger.debug("Number of records in validation set: %d", len(Xval))
mu, sigma2 = estimateGaussian(X)
p = multivariateGaussian(X, mu, sigma2)
pval = multivariateGaussian(Xval, mu, sigma2)
F1val, epsilon = selectThreshold(Yval, pval)
outliers = p < epsilon
# Outliers in training set
listOfOl = findIndices(outliers)
# Save epsilon and F1 score
self.storage["anomalies"] = (
epsilon,
F1val,
mu.tolist(),
sigma2.tolist(),
)
async def train(self, sources: SourcesContext) -> None:
# X and Y data
x = []
y = []
# Go through all records that have the feature we're training on and the
# feature we want to predict.
async for record in sources.with_features(
[self.config.feature.name, self.config.predict.name]):
x.append(record.feature(self.config.feature.name))
y.append(record.feature(self.config.predict.name))
# Use self.logger to report how many records are being used for training
self.logger.debug("Number of training records: %d", len(x))
# Save m, b, and accuracy
self.storage["regression_line"] = best_fit_line(x, y)
async def accuracy(self, sources: SourcesContext) -> Accuracy:
# Load saved anomalies
anomalies = self.storage.get("anomalies", None)
# Ensure the model has been trained before we try to make a prediction
if anomalies is None:
raise ModelNotTrained("Train model before assessing for accuracy.")
epsilon, _F1val, mu, sigma2 = anomalies
X = []
Y = []
# Go through all records that have the feature we're training on and the
# feature we want to predict.
async for record in sources.with_features(
self.features + [self.parent.config.predict.name]):
record_data = []
for feature in record.features(self.features).values():
record_data.extend(
[feature] if np.isscalar(feature) else feature)
X.append(record_data)
Y.append(record.feature(self.parent.config.predict.name))
self.logger.debug("Number of test records: %d", len(X))
# Number of features
nof = len(self.features)
X = np.reshape(X, (len(X), nof))
Y = np.reshape(Y, (len(Y), 1))
mu = np.array(mu)
sigma2 = np.array(sigma2)
p = multivariateGaussian(X, mu, sigma2)
pred = (p < epsilon).astype(int)
F1 = getF1(Y, pred)
outliers = p < epsilon
listOfOl = findIndices(outliers)
accuracy = F1
# Update the accuracy
self.storage["anomalies"] = epsilon, F1, mu.tolist(), sigma2.tolist()
return Accuracy(accuracy)
async def predict(
self, sources: SourcesContext
) -> AsyncIterator[Tuple[Record, Any, float]]:
# Ensure the model has been trained before we try to make a prediction
if self.separating_line is None:
raise ModelNotTrained("Train model before prediction.")
target = self.config.predict.name
async for record in sources.with_features(
self.parent.config.features.names()):
feature_data = record.features(self.features)
record.predicted(
target,
self.predict_input(feature_data[self.features[0]]),
self.separating_line[2],
)
yield record
async def predict(
self, sources: SourcesContext
) -> AsyncIterator[Tuple[Record, Any, float]]:
# Iterate through each record that needs a prediction
if self.lm_trained is None:
raise ModelNotTrained("Train model before prediction.")
async for record in sources.with_features(
self.parent.config.features.names()
):
feature_data = record.features(self.features)
predict = self.pd.DataFrame(feature_data, index=[0])
preds = self.lm_predictor.compute(predict, self.lm_trained)
target = self.parent.config.predict.name
record.predicted(target, preds.prediction, float("nan"))
# Yield the record to the caller
yield record
async def predict(self, sources: SourcesContext) -> AsyncIterator[Record]:
# Load saved regression line
regression_line = self.storage.get("regression_line", None)
# Ensure the model has been trained before we try to make a prediction
if regression_line is None:
raise ModelNotTrained("Train model before prediction")
# Expand the regression_line into named variables
m, b, accuracy = regression_line
# Iterate through each record that needs a prediction
async for record in sources.with_features([self.config.feature.name]):
# Grab the x data from the record
x = record.feature(self.config.feature.name)
# Calculate y
y = m * x + b
# Set the calculated value with the estimated accuracy
record.predicted(self.config.predict.name, y, accuracy)
# Yield the record to the caller
yield record
async def get_test_records(self, sources: SourcesContext):
ret_record = []
async for record in sources.with_features(self.features):
ret_record.append(record)
return ret_record
async def predict(self, sources: SourcesContext) -> AsyncIterator[Record]:
async for record in sources.with_features(["by_ten"]):
record.predicted("Salary",
record.feature("by_ten") * 10, float(record.key))
yield record
async def get_input_data(self, sources: SourcesContext) -> list:
saved_records = []
async for record in sources.with_features(
self.config.features.names()):
saved_records.append(record)
return saved_records