尝试使用tensorflow创建一个预测贷款申请的模型。这是下载数据集的链接。我使用LinerClassifier模型进行预引用。该数据集可在kaggle上获得，并且可以轻松下载。Tensorflow版本：2.3.1Python版本：3.7.3
train_df = pd.read_csv('Loan_train.csv')
test_df = pd.read_csv('Loan_test.csv')
train_df.head()
df = pd.concat([train_df, test_df])
df = df.fillna(method='ffill')
df = df.dropna()
CATEGORICAL_COLUMNS = ['Gender', 'Married', 'Education', 'Self_Employed','Dependents', 'Property_Area']
NUMERIC_COLUMNS = ['ApplicantIncome', 'CoapplicantIncome', 'LoanAmount', 'Loan_Amount_Term', 'Credit_History']
feature_columns = []
for feature_name in CATEGORICAL_COLUMNS:
vocabulary = df[feature_name].unique() # gets a list of all unique values from given feature column
feature_columns.append(tf.feature_column.categorical_column_with_vocabulary_list(feature_name, vocabulary))
for feature_name in NUMERIC_COLUMNS:
feature_columns.append(tf.feature_column.numeric_column(feature_name, dtype=tf.float64))
print(feature_columns)
# Split data into train and test datasets
from sklearn.model_selection import train_test_split
columns = CATEGORICAL_COLUMNS + NUMERIC_COLUMNS
X = df[columns]
Y = df['Loan_Status']
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.15, random_state=0)
def make_input_fn(data_df, label_df, num_epochs=10, shuffle=True, batch_size=32):
def input_function(): # inner function, this will be returned
ds = tf.data.Dataset.from_tensor_slices((dict(data_df), label_df)) # create tf.data.Dataset object with data and its label
if shuffle:
ds = ds.shuffle(1000) # randomize order of data
ds = ds.batch(batch_size).repeat(num_epochs) # split dataset into batches of 32 and repeat process for number of epochs
return ds # return a batch of the dataset
return input_function # return a function object for use
train_input_fn = make_input_fn(X_train, y_train) # here we will call the input_function that was returned to us to get a dataset object we can feed to the model
test_input_fn = make_input_fn(X_test, y_test, num_epochs=1, shuffle=False)
classifier = tf.estimator.LinearClassifier(
feature_columns=feature_columns,
# The model must choose between 2 classes.
n_classes=2)
# training model
classifier.train(train_input_fn)
错误消息
UnimplementedError: Cast string to float is not supported
[[node head/losses/Cast (defined at /home/dipeshkusrai/.local/lib/python3.7/site-packages/tensorflow_estimator/python/estimator/head/binary_class_head.py:258) ]]
您输入的数据集的列名似乎是一个字符串，并且该列中的值是浮动的，请尝试跳过第一行，同时使用skiprows=1从csv转换为DataFrame