您可以创建一个自定义模型字段，将数据保存到存储中的文件，并将相对文件路径保存到数据库。
以下是如何models.CharField在应用程序中进行子类化fields.py：
import os
from django.core.exceptions import ValidationError
from django.core.files.storage import default_storage
from django.db import models
from django.utils.translation import gettext_lazy as _
class DataFrameField(models.CharField):
"""
custom field to save Pandas DataFrame to the hdf5 file format
as advised in the official pandas documentation:
http://pandas.pydata.org/pandas-docs/stable/io.html#io-perf
"""
attr_class = DataFrame
default_error_messages = {
"invalid": _("Please provide a DataFrame object"),
}
def __init__(
self,
verbose_name=None,
name=None,
upload_to="data",
storage=None,
unique_fields=[],
**kwargs
):
self.storage = storage or default_storage
self.upload_to = upload_to
self.unique_fields = unique_fields
kwargs.setdefault("max_length", 100)
super().__init__(verbose_name, name, **kwargs)
def deconstruct(self):
name, path, args, kwargs = super().deconstruct()
if kwargs.get("max_length") == 100:
del kwargs["max_length"]
if self.upload_to != "data":
kwargs["upload_to"] = self.upload_to
if self.storage is not default_storage:
kwargs["storage"] = self.storage
kwargs["unique_fields"] = self.unique_fields
return name, path, args, kwargs
__init__和deconstruct方法非常受 Django 原始FileField的启发。还有一个附加unique_fields参数可用于创建可预测的唯一文件名。
def from_db_value(self, value, expression, connection):
"""
return a DataFrame object from the filepath saved in DB
"""
if value is None:
return value
return self.retrieve_dataframe(value)
def get_absolute_path(self, value):
"""
return absolute path based on the value saved in the Database.
"""
return self.storage.path(value)
def retrieve_dataframe(self, value):
"""
return the pandas DataFrame and add filepath as property to Dataframe
"""
# read dataframe from storage
absolute_filepath = self.get_absolute_path(value)
dataframe = read_hdf(absolute_filepath)
# add relative filepath as instance property for later use
dataframe.filepath = value
return dataframe
from_db_value您使用基于数据库中保存的文件路径的方法将 DataFrame 从存储加载到内存。
在检索 DataFrame 时，您还将文件路径作为实例属性添加到它，以便在将 DataFrame 保存回数据库时可以使用该值。
def pre_save(self, model_instance, add):
"""
save the dataframe field to an hdf5 field before saving the model
"""
dataframe = super().pre_save(model_instance, add)
if dataframe is None:
return dataframe
if not isinstance(dataframe, DataFrame):
raise ValidationError(
self.error_messages["invalid"], code="invalid",
)
self.save_dataframe_to_file(dataframe, model_instance)
return dataframe
def get_prep_value(self, value):
"""
save the value of the dataframe.filepath set in pre_save
"""
if value is None:
return value
# save only the filepath to the database
if value.filepath:
return value.filepath
def save_dataframe_to_file(self, dataframe, model_instance):
"""
write the Dataframe into an hdf5 file in storage at filepath
"""
# try to retrieve the filepath set when loading from the database
if not dataframe.get("filepath"):
dataframe.filepath = self.generate_filepath(model_instance)
full_filepath = self.storage.path(dataframe.filepath)
# Create any intermediate directories that do not exist.
# shamelessly copied from Django's original Storage class
directory = os.path.dirname(full_filepath)
if not os.path.exists(directory):
try:
if self.storage.directory_permissions_mode is not None:
# os.makedirs applies the global umask, so we reset it,
# for consistency with file_permissions_mode behavior.
old_umask = os.umask(0)
try:
os.makedirs(directory, self.storage.directory_permissions_mode)
finally:
os.umask(old_umask)
else:
os.makedirs(directory)
except FileExistsError:
# There's a race between os.path.exists() and os.makedirs().
# If os.makedirs() fails with FileExistsError, the directory
# was created concurrently.
pass
if not os.path.isdir(directory):
raise IOError("%s exists and is not a directory." % directory)
# save to storage
dataframe.to_hdf(full_filepath, "df", mode="w", format="fixed")
def generate_filepath(self, instance):
"""
return a filepath based on the model's class name, dataframe_field and unique fields
"""
# create filename based on instance and field name
class_name = instance.__class__.__name__
# generate unique id from unique fields:
unique_id_values = []
for field in self.unique_fields:
unique_field_value = getattr(instance, field)
# get field value or id if the field value is a related model instance
unique_id_values.append(
str(getattr(unique_field_value, "id", unique_field_value))
)
# filename, for example: route_data_<uuid>.h5
filename = "{class_name}_{field_name}_{unique_id}.h5".format(
class_name=class_name.lower(),
field_name=self.name,
unique_id="".join(unique_id_values),
)
# generate filepath
dirname = self.upload_to
filepath = os.path.join(dirname, filename)
return self.storage.generate_filename(filepath)
使用方法将 DataFrame 保存到 hdf5 文件，pre_save并将文件路径保存到数据库中get_prep_value.
在我的情况下，它有助于使用uuid模型字段来创建唯一的文件名，因为对于新模型实例，方法pk中尚不可用pre-save，但uuid值是。
然后，您可以在您的models.py:
from .fields import DataFrameField
# track data as a pandas DataFrame
data = DataFrameField(null=True, upload_to="data", unique_fields=["uuid"])
请注意，您不能在 Django 管理员或模型表单中使用此字段。这将需要在自定义表单小部件上进行额外的工作，以在前端编辑 DataFrame 内容，可能作为表格。
另请注意，对于测试，我必须MEDIA_ROOT使用tempfile使用临时目录覆盖设置，以防止在实际媒体文件夹中创建无用文件。