def test_predict(self):
self.required_plugins("dffml-model-scikit")
# Import SciKit modules
dffml_model_scikit = importlib.import_module("dffml_model_scikit")
# Instantiate the model
model = dffml_model_scikit.LinearRegressionModel(
directory=self.mktempdir(),
predict=Feature("Salary", int, 1),
features=Features(
Feature("Years", int, 1),
Feature("Expertise", int, 1),
Feature("Trust", float, 1),
),
)
training_data = CSVSource(filename=self.train_filename)
test_data = CSVSource(filename=self.test_filename)
predict_data = CSVSource(filename=self.predict_filename)
# Train the model
train(model, training_data)
# Assess accuracy
accuracy(model, test_data)
# Make prediction
predictions = [
prediction for prediction in predict(model, predict_data)
]
self.assertEqual(round(predictions[0][2]["Salary"]["value"]), 70)
self.assertEqual(round(predictions[1][2]["Salary"]["value"]), 80)
def main():
# Train the model
train(model, "train.csv")
# Assess accuracy
print("Accuracy:", accuracy(model, "test.csv"))
# Make prediction
for i, features, prediction in predict(model, "predict.csv"):
features["TARGET"] = prediction["TARGET"]["value"]
print(features)
def main():
# Train the model
train(model, "train.csv")
# Assess accuracy
scorer = MeanSquaredErrorAccuracy()
print(
"Accuracy:",
score(model, scorer, Feature("TARGET", float, 1), "test.csv"),
)
# Make prediction
for i, features, prediction in predict(model, "predict.csv"):
features["TARGET"] = prediction["TARGET"]["value"]
print(features)
from dffml import CSVSource, Features, Feature
from dffml.noasync import train, accuracy, predict
from dffml_model_scratch.logisticregression import LogisticRegression
model = LogisticRegression(
features=Features(Feature("f1", float, 1)),
predict=Feature("ans", int, 1),
)
# Train the model
train(model, "dataset.csv")
# Assess accuracy (alternate way of specifying data source)
print("Accuracy:", accuracy(model, CSVSource(filename="dataset.csv")))
# Make prediction
for i, features, prediction in predict(model, {"f1": 0.8, "ans": 0}):
features["ans"] = prediction["ans"]["value"]
print(features)
from dffml import CSVSource, DefFeature
from dffml.noasync import train, accuracy, predict
from dffml_model_transformers.ner.ner_model import NERModel
model = NERModel(
sid=DefFeature("SentenceId", int, 1),
words=DefFeature("Words", str, 1),
predict=DefFeature("Tag", str, 1),
model_architecture_type="distilbert",
model_name_or_path="distilbert-base-cased",
epochs=1,
no_cuda=True,
)
# Train the model
train(model, "train.csv")
# Assess accuracy (alternate way of specifying data source)
print("Accuracy:", accuracy(model, CSVSource(filename="train.csv")))
# Make prediction
for i, features, prediction in predict(
model,
{"SentenceID": 1, "Words": "DFFML models can do NER",},
{"SentenceID": 2, "Words": "DFFML models can do regression",},
):
features["Tag"] = prediction["Tag"]["value"]
print(features)
Feature("Years", int, 1),
Feature("Expertise", int, 1),
Feature("Trust", float, 1),
),
predict=Feature("Salary", int, 1),
directory="tempdir",
)
# Train the model
train(model, "train.csv")
# Assess accuracy (alternate way of specifying data source)
print("Accuracy:", accuracy(model, CSVSource(filename="test.csv")))
# Make prediction
for i, features, prediction in predict(
model,
{
"Years": 6,
"Expertise": 13,
"Trust": 0.7
},
{
"Years": 7,
"Expertise": 15,
"Trust": 0.8
},
):
features["Salary"] = prediction["Salary"]["value"]
print(features)
}, #"Expertise": 5, "Trust": 0.3,
{
"Years": 3,
"Salary": 40
}, #"Expertise": 7, "Trust": 0.4,
)
# Assess accuracy
print(
"Accuracy:",
accuracy(
model,
{
"Years": 4,
"Salary": 50
}, #"Expertise": 9, "Trust": 0.5,
{
"Years": 5,
"Salary": 60
}, #"Expertise": 11, "Trust": 0.6,
),
)
# Make prediction
for i, features, prediction in predict(
model,
{"Years": 6}, #"Expertise": 13, "Trust": 0.7
{"Years": 7}, #"Expertise": 15, "Trust": 0.8
):
features["Salary"] = prediction["Salary"]["value"]
print(features)
from dffml import Feature
from dffml.noasync import train, accuracy, predict
from myslr import MySLRModel
# Configure the model
model = MySLRModel(
feature=Feature("Years", int, 1),
predict=Feature("Salary", int, 1),
directory="model",
)
# Train the model
train(model, "train.csv")
# Assess accuracy
print("Accuracy:", accuracy(model, "test.csv"))
# Make predictions
for i, features, prediction in predict(model, "predict.csv"):
features["Salary"] = prediction["Salary"]["value"]
print(features)
from dffml import CSVSource, Features, Feature
from dffml.noasync import train, accuracy, predict
from dffml_model_tensorflow_hub.text_classifier import TextClassificationModel
model = TextClassificationModel(
features=Features(Feature("sentence", str, 1)),
predict=Feature("sentiment", int, 1),
classifications=[0, 1, 2],
clstype=int,
directory="tempdir",
)
# Train the model
train(model, "train.csv")
# Assess accuracy (alternate way of specifying data source)
print("Accuracy:", accuracy(model, CSVSource(filename="test.csv")))
# Make prediction
for i, features, prediction in predict(
model,
{"sentence": "This track is horrible"},
):
features["sentiment"] = prediction["sentiment"]["value"]
print(features)
epochs=3000,
steps=20000,
classifications=[0, 1, 2],
clstype=int,
)
# Train the model
train(model, "iris_training.csv")
# Assess accuracy (alternate way of specifying data source)
print("Accuracy:", accuracy(model, CSVSource(filename="iris_test.csv")))
# Make prediction
for i, features, prediction in predict(
model,
{
"PetalLength": 4.2,
"PetalWidth": 1.5,
"SepalLength": 5.9,
"SepalWidth": 3.0,
},
{
"PetalLength": 5.4,
"PetalWidth": 2.1,
"SepalLength": 6.9,
"SepalWidth": 3.1,
},
):
features["classification"] = prediction["classification"]["value"]
print(features)
from dffml import CSVSource, Features, Feature
from dffml.noasync import train, accuracy, predict
from dffml_model_tensorflow.dnnr import DNNRegressionModel
model = DNNRegressionModel(
features=Features(Feature("Feature1", float, 1),
Feature("Feature2", float, 1)),
predict=Feature("TARGET", float, 1),
epochs=300,
steps=2000,
hidden=[8, 16, 8],
directory="tempdir",
)
# Train the model
train(model, "train.csv")
# Assess accuracy (alternate way of specifying data source)
print("Accuracy:", accuracy(model, CSVSource(filename="test.csv")))
# Make prediction
for i, features, prediction in predict(model, {
"Feature1": 0.21,
"Feature2": 0.18,
"TARGET": 0.84
}):
features["TARGET"] = prediction["TARGET"]["value"]
print(features)
