def python_random_split(data, ratio=0.75, seed=42):
"""Pandas random splitter
The splitter randomly splits the input data.
Args:
data (pd.DataFrame): Pandas DataFrame to be split.
ratio (float or list): Ratio for splitting data. If it is a single float number
it splits data into two halves and the ratio argument indicates the ratio
of training data set; if it is a list of float numbers, the splitter splits
data into several portions corresponding to the split ratios. If a list is
provided and the ratios are not summed to 1, they will be normalized.
seed (int): Seed.
Returns:
list: Splits of the input data as pd.DataFrame.
"""
multi_split, ratio = process_split_ratio(ratio)
if multi_split:
splits = split_pandas_data_with_ratios(data, ratio, shuffle=True, seed=seed)
splits_new = [x.drop('split_index', axis=1) for x in splits]
return splits_new
else:
return sk_split(data, test_size=None, train_size=ratio, random_state=seed)
def python_random_split(data, ratio=0.75, seed=42):
"""Pandas random splitter
The splitter randomly splits the input data.
Args:
data (pd.DataFrame): Pandas DataFrame to be split.
ratio (float or list): Ratio for splitting data. If it is a single float number
it splits data into two halves and the ratio argument indicates the ratio
of training data set; if it is a list of float numbers, the splitter splits
data into several portions corresponding to the split ratios. If a list is
provided and the ratios are not summed to 1, they will be normalized.
seed (int): Seed.
Returns:
list: Splits of the input data as pd.DataFrame.
"""
multi_split, ratio = process_split_ratio(ratio)
if multi_split:
splits = split_pandas_data_with_ratios(data,
ratio,
shuffle=True,
seed=seed)
splits_new = [x.drop('split_index', axis=1) for x in splits]
return splits_new
else:
return sk_split(data,
test_size=None,
train_size=ratio,
random_state=seed)
def main():
path = 'heart.csv'
feature, target = Read_data(path)
save_path = "test-output/"
# 資料切分
train_feature, test_feature, train_target, test_target = sk_split(feature, target, test_size=0.3, random_state=10) # 以隨機的方式資料分割 並給隨機種子固定隨機模式
# 模型選擇
model = clf_rtree(max_depth=5,min_samples_leaf=4,n_estimators=10,random_state=10) # 限制決策樹最大深度 避免overfitting
model.fit(train_feature, train_target)
# 模型預測
pre_target = model.predict(test_feature)
# true false positive sensitive ROC
t_f_postive(test_target,pre_target)
# accurancy 正確率
scor = model.score(test_feature,test_target)
print('scor: ',scor)
# 各feature 的影響程度
var_influence(model, test_feature, save_path)
# 畫隨機森林樹出來
column = train_feature.columns
draw_tree(model , column , save_path)
def train(model, x, y):
record_path = 'model_save/training.csv'
train_x, test_x, train_y, test_y = sk_split(
x, y, test_size=0.3, random_state=10) # 以隨機的方式資料分割 並給隨機種子固定隨機模式
train_y = keras.utils.to_categorical(train_y, 2)
test_y = keras.utils.to_categorical(test_y, 2)
adam = Adam(lr=0.05, decay=3e-4)
model.compile(loss='categorical_crossentropy',
optimizer=adam,
metrics=['accuracy'])
# 將每次訓練的結果已CSV檔形式儲存起來 => 可以用來視覺化訓練情況
csv_logger = CSVLogger(record_path)
filepath = 'model_save'
checkpointer = ModelCheckpoint(filepath=filepath +
'/weights-{val_acc:.2f}.hdf5',
verbose=1,
save_best_only=True,
period=10)
# model.fit(train_x, train_y, batch_size=20, epochs=500, validation_data=(test_x,test_y), verbose=1, callbacks=[csv_logger, checkpointer])
train_plot(record_path)
analizy(filepath, x, y)
