概述

• 是一个在keras基础上的自动机器学习库
• 模型训练模型门槛较低,每个人都可以使用机器学习
• 当前支持的训练任务有
  • 图像分类
  • 图像识别
  • 文本分类
  • 文本识别
  • 结构数据分类
  • 结构数据识别
• 未来将支持的训练任务
  • 图像检测
  • 图像分割
  • 时间序列预测
• 完整模型训练样例

安装

[~]# pip install autokeras

图像分类-简单样例

# Initialize the image classifier.
clf = ak.ImageClassifier(overwrite=True, max_trials=1)
# Feed the image classifier with training data.
clf.fit(x_train, y_train, epochs=10)

# Predict with the best model.
predicted_y = clf.predict(x_test)
print(predicted_y)

# Evaluate the best model with testing data.
print(clf.evaluate(x_test, y_test))

图像回归-简单样例

# Initialize the image regressor.
reg = ak.ImageRegressor(overwrite=True, max_trials=1)
# Feed the image regressor with training data.
reg.fit(x_train, y_train, epochs=2)

# Predict with the best model.
predicted_y = reg.predict(x_test)
print(predicted_y)

# Evaluate the best model with testing data.
print(reg.evaluate(x_test, y_test))

文本分类

# Initialize the text classifier.
clf = ak.TextClassifier(
    overwrite=True, max_trials=1
)  # It only tries 1 model as a quick demo.
# Feed the text classifier with training data.
clf.fit(x_train, y_train, epochs=2)
# Predict with the best model.
predicted_y = clf.predict(x_test)
# Evaluate the best model with testing data.
print(clf.evaluate(x_test, y_test))

文本回归

# Initialize the text regressor.
reg = ak.TextRegressor(overwrite=True, max_trials=1)  # It tries 10 different models.
# Feed the text regressor with training data.
reg.fit(x_train, y_train, epochs=2)
# Predict with the best model.
predicted_y = reg.predict(x_test)
# Evaluate the best model with testing data.
print(reg.evaluate(x_test, y_test))

结构体数据分类

# Initialize the structured data classifier.
clf = ak.StructuredDataClassifier(
    overwrite=True, max_trials=3
)  # It tries 3 different models.
# Feed the structured data classifier with training data.
clf.fit(
    # The path to the train.csv file.
    train_file_path,
    # The name of the label column.
    "survived",
    epochs=10,
)
# Predict with the best model.
predicted_y = clf.predict(test_file_path)
# Evaluate the best model with testing data.
print(clf.evaluate(test_file_path, "survived"))

# x_train as pandas.DataFrame, y_train as pandas.Series
x_train = pd.read_csv(train_file_path)
print(type(x_train))  # pandas.DataFrame
y_train = x_train.pop("survived")
print(type(y_train))  # pandas.Series

# You can also use pandas.DataFrame for y_train.
y_train = pd.DataFrame(y_train)
print(type(y_train))  # pandas.DataFrame

# You can also use numpy.ndarray for x_train and y_train.
x_train = x_train.to_numpy()
y_train = y_train.to_numpy()
print(type(x_train))  # numpy.ndarray
print(type(y_train))  # numpy.ndarray

# Preparing testing data.
x_test = pd.read_csv(test_file_path)
y_test = x_test.pop("survived")

# It tries 10 different models.
clf = ak.StructuredDataClassifier(overwrite=True, max_trials=3)
# Feed the structured data classifier with training data.
clf.fit(x_train, y_train, epochs=10)
# Predict with the best model.
predicted_y = clf.predict(x_test)
# Evaluate the best model with testing data.
print(clf.evaluate(x_test, y_test))

结构体数据回归

# Initialize the structured data regressor.
reg = ak.StructuredDataRegressor(
    overwrite=True, max_trials=3
)  # It tries 3 different models.
# Feed the structured data regressor with training data.
reg.fit(
    # The path to the train.csv file.
    train_file_path,
    # The name of the label column.
    "Price",
    epochs=10,
)
# Predict with the best model.
predicted_y = reg.predict(test_file_path)
# Evaluate the best model with testing data.
print(reg.evaluate(test_file_path, "Price"))

# x_train as pandas.DataFrame, y_train as pandas.Series
x_train = pd.read_csv(train_file_path)
print(type(x_train))  # pandas.DataFrame
y_train = x_train.pop("Price")
print(type(y_train))  # pandas.Series

# You can also use pandas.DataFrame for y_train.
y_train = pd.DataFrame(y_train)
print(type(y_train))  # pandas.DataFrame

# You can also use numpy.ndarray for x_train and y_train.
x_train = x_train.to_numpy()
y_train = y_train.to_numpy()
print(type(x_train))  # numpy.ndarray
print(type(y_train))  # numpy.ndarray

# Preparing testing data.
x_test = pd.read_csv(test_file_path)
y_test = x_test.pop("Price")

# It tries 10 different models.
reg = ak.StructuredDataRegressor(max_trials=3, overwrite=True)
# Feed the structured data regressor with training data.
reg.fit(x_train, y_train, epochs=10)
# Predict with the best model.
predicted_y = reg.predict(x_test)
# Evaluate the best model with testing data.
print(reg.evaluate(x_test, y_test))

时间序列

dataset = tf.keras.utils.get_file(
    fname="AirQualityUCI.csv",
    origin="https://archive.ics.uci.edu/ml/machine-learning-databases/00360/"
           "AirQualityUCI.zip",
    extract=True,
)

dataset = pd.read_csv(dataset, sep=";")
dataset = dataset[dataset.columns[:-2]]
dataset = dataset.dropna()
dataset = dataset.replace(",", ".", regex=True)

val_split = int(len(dataset) * 0.7)
data_train = dataset[:val_split]
validation_data = dataset[val_split:]

data_x = data_train[
    [
        "CO(GT)",
        "PT08.S1(CO)",
        "NMHC(GT)",
        "C6H6(GT)",
        "PT08.S2(NMHC)",
        "NOx(GT)",
        "PT08.S3(NOx)",
        "NO2(GT)",
        "PT08.S4(NO2)",
        "PT08.S5(O3)",
        "T",
        "RH",
    ]
].astype("float64")

data_x_val = validation_data[
    [
        "CO(GT)",
        "PT08.S1(CO)",
        "NMHC(GT)",
        "C6H6(GT)",
        "PT08.S2(NMHC)",
        "NOx(GT)",
        "PT08.S3(NOx)",
        "NO2(GT)",
        "PT08.S4(NO2)",
        "PT08.S5(O3)",
        "T",
        "RH",
    ]
].astype("float64")

# Data with train data and the unseen data from subsequent time steps.
data_x_test = dataset[
    [
        "CO(GT)",
        "PT08.S1(CO)",
        "NMHC(GT)",
        "C6H6(GT)",
        "PT08.S2(NMHC)",
        "NOx(GT)",
        "PT08.S3(NOx)",
        "NO2(GT)",
        "PT08.S4(NO2)",
        "PT08.S5(O3)",
        "T",
        "RH",
    ]
].astype("float64")

data_y = data_train["AH"].astype("float64")

data_y_val = validation_data["AH"].astype("float64")

print(data_x.shape)  # (6549, 12)
print(data_y.shape)  # (6549,)

predict_from = 1
predict_until = 10
lookback = 3
clf = ak.TimeseriesForecaster(
    lookback=lookback,
    predict_from=predict_from,
    predict_until=predict_until,
    max_trials=1,
    objective="val_loss",
)
# Train the TimeSeriesForecaster with train data
clf.fit(
    x=data_x,
    y=data_y,
    validation_data=(data_x_val, data_y_val),
    batch_size=32,
    epochs=10,
)
# Predict with the best model(includes original training data).
predictions = clf.predict(data_x_test)
print(predictions.shape)
# Evaluate the best model with testing data.
print(clf.evaluate(data_x_val, data_y_val))