我对模型做了一些小的改动。现在，我没有得到准确的 [0.5, 0.5]。
结果：
[[0.61482537 0.3851746 ]
[0.5121426 0.48785746]
[0.48058605 0.51941395]
[0.48913187 0.51086813]
[0.45480043 0.5451996 ]
[0.48933673 0.5106633 ]
[0.43431875 0.5656812 ]
[0.55314165 0.4468583 ]
[0.5365097 0.4634903 ]
[0.54371756 0.45628244]]
实施：
import datetime
import os
import numpy as np
import pandas as pd
import tensorflow as tf
from gpu_limiter import limit_gpu
from pipe_functions import csv_to_df, dataframe_to_dataset
from sklearn.model_selection import train_test_split
from tensorflow import keras
from tensorflow.keras.layers import BatchNormalization, Dense, DenseFeatures, Dropout, Input
from tensorflow.keras.callbacks import TensorBoard, ModelCheckpoint
import tensorflow.keras.backend as K
from tensorflow.data import Dataset
# Test GPU availability and instantiate memory growth limitation if True:
if tf.test.is_gpu_available():
print('GPU Available\n')
limit_gpu()
else:
print('Running on CPU')
df = csv_to_df("./csv_files")
# Format & organise imported data, making the "Date" column the new index:
df['Date'] = pd.to_datetime(df['Date'])
df = df[['Date', 'Div', 'HomeTeam', 'AwayTeam', 'FTHG', 'FTAG']].dropna().set_index('Date').sort_index()
df['Over_2.5'] = (df['FTHG'] + df['FTAG'] > 2.5).astype(int)
df = df.drop(['FTHG', 'FTAG'], axis=1)
# Split data into training, validation and testing data:
# Note: random_state variable set to ensure reproducibility.
train, test = train_test_split(df, test_size=0.05, random_state=42)
train, val = train_test_split(train, test_size=0.05, random_state=42)
# print(df['Over_2.5'].value_counts()) # Check that data is balanced.
# Create datasets from train, val & test dataframes:
target_col = 'Over_2.5'
batch_size = 32
def df_to_dataset(features: np.ndarray, labels: np.ndarray, shuffle=True, batch_size=8) -> Dataset:
ds = Dataset.from_tensor_slices(({"feature": features}, {"target": labels}))
if shuffle:
ds = ds.shuffle(buffer_size=len(features))
ds = ds.batch(batch_size)
return ds
def get_feature_transform() -> DenseFeatures:
# Format features into feature columns to ensure data is in the correct format for feeding into the model:
feature_cols = []
for column in filter(lambda x: x != target_col, df.columns):
feature_cols.append(tf.feature_column.embedding_column(tf.feature_column.categorical_column_with_vocabulary_list(
key=column, vocabulary_list=df[column].unique()), dimension=5))
return DenseFeatures(feature_cols)
# Transforms all features into dense tensors.
feature_transform = get_feature_transform()
train_features = feature_transform(dict(train)).numpy()
val_features = feature_transform(dict(val)).numpy()
test_features = feature_transform(dict(test)).numpy()
train_dataset = df_to_dataset(train_features, train[target_col].values, shuffle=True, batch_size=batch_size)
val_dataset = df_to_dataset(val_features, val[target_col].values, shuffle=True, batch_size=batch_size) # Shuffle not required to validation data.
test_dataset = df_to_dataset(test_features, test[target_col].values, shuffle=True, batch_size=batch_size) # Shuffle not required to test data.
# Create Keras Functional API:
# Create a feature layer from the feature columns, to be placed at the input layer of the model:
def build_model(input_shape: tuple) -> keras.Model:
input_layer = keras.Input(shape=input_shape, name='feature')
model = Dense(units=1028, activation='relu', kernel_initializer='normal', name='dense0')(input_layer) # Hidden Layer 1.
model = BatchNormalization(name='bc0')(model)
model = Dense(units=1028, activation='relu', kernel_initializer='normal', name='dense1')(model) # Hidden Layer 2.
model = Dropout(rate=0.1)(model)
model = BatchNormalization(name='bc1')(model)
model = Dense(units=100, activation='relu', kernel_initializer='normal', name='dense2')(model) # Hidden Layer 3.
model = Dropout(rate=0.25)(model)
model = BatchNormalization(name='bc2')(model)
model = Dense(units=50, activation='relu', kernel_initializer='normal', name='dense3')(model) # Hidden Layer 4.
model = Dropout(rate=0.4)(model)
model = BatchNormalization(name='bc3')(model)
output_layer = Dense(units=2, activation='softmax', kernel_initializer='normal', name='target')(model) # Output layer.
model = keras.Model(inputs=input_layer, outputs=output_layer, name='better-than-chance')
# Compile the model:
model.compile(
optimizer=keras.optimizers.Adam(learning_rate=0.001),
loss='mse',
metrics=['accuracy']
)
return model
# # Create a TensorBoard log file (time appended) directory for every run of the model:
# directory = ".\\logs\\" + str(datetime.datetime.now().strftime("%Y%m%d-%H%M%S"))
# os.mkdir(directory)
# # Create a TensorBoard callback to log a record of model performance for every 1 epoch:
# tensorboard_callback = TensorBoard(log_dir=directory, histogram_freq=1, write_graph=True, write_images=True)
# Run "tensorboard --logdir .\logs" in anaconda prompt to review & compare logged results.
# Note: Make sure that the correct environment is activated before running.
model = build_model((train_features.shape[1],))
model.summary()
# checkpoint = ModelCheckpoint('model-{epoch:03d}.h5', verbose=1, monitor='val_loss',save_best_only=True, mode='auto')
# Fit the model to the training dataset and validate against the validation dataset between epochs:
model.fit(
train_dataset,
validation_data=val_dataset,
epochs=10)
# callbacks=[checkpoint]
# Saves and reloads model.
# model.save("./model.h5")
# model_from_saved = keras.models.load_model("./model.h5")
# Evaluate model accuracy against test dataset:
# scores, accuracy = model.evaluate(train_dataset)
# print('Accuracy:', accuracy)
##############
## OPTIONAL ##
##############
# DUBUGGING
# inp = model.input # input placeholder
# outputs = [layer.output for layer in model.layers] # all layer outputs
# functors = [K.function([inp], [out]) for out in outputs] # evaluation functions
# # Testing
# layer_outs = [func([test_features]) for func in functors]
# print(layer_outs)
# # # Form a prediction based on inputs:
prediction = model.predict({"feature": test_features[:10]})
print(prediction)
您可以做的一件事是尝试一些集成学习方法，例如
RandomForest
和
XGBoost
并比较结果。
您应该尝试将其他关键绩效指标 (KPI) 添加到
您的数据，然后尝试拟合模型。