src/autotrain/preprocessor/vision.py [438:495]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        return metadata

    def __post_init__(self):
        # Check if train data path exists
        if not os.path.exists(self.train_data):
            raise ValueError(f"{self.train_data} does not exist.")

        # check if self.train_data contains at least 5 image files in jpeg, png or jpg format only
        train_image_files = [f for f in os.listdir(self.train_data) if f.endswith(ALLOWED_EXTENSIONS)]
        if len(train_image_files) < 5:
            raise ValueError(f"{self.train_data} should contain at least 5 jpeg, png or jpg files.")

        # check if self.train_data contains a metadata.jsonl file
        if "metadata.jsonl" not in os.listdir(self.train_data):
            raise ValueError(f"{self.train_data} should contain a metadata.jsonl file.")

        # Check if valid data path exists
        if self.valid_data:
            if not os.path.exists(self.valid_data):
                raise ValueError(f"{self.valid_data} does not exist.")

            # check if self.valid_data contains at least 5 image files in jpeg, png or jpg format only
            valid_image_files = [f for f in os.listdir(self.valid_data) if f.endswith(ALLOWED_EXTENSIONS)]
            if len(valid_image_files) < 5:
                raise ValueError(f"{self.valid_data} should contain at least 5 jpeg, png or jpg files.")

            # check if self.valid_data contains a metadata.jsonl file
            if "metadata.jsonl" not in os.listdir(self.valid_data):
                raise ValueError(f"{self.valid_data} should contain a metadata.jsonl file.")

    def split(self, df):
        train_df, valid_df = train_test_split(
            df,
            test_size=self.test_size,
            random_state=self.seed,
        )
        train_df = train_df.reset_index(drop=True)
        valid_df = valid_df.reset_index(drop=True)
        return train_df, valid_df

    def prepare(self):
        random_uuid = uuid.uuid4()
        cache_dir = os.environ.get("HF_HOME")
        if not cache_dir:
            cache_dir = os.path.join(os.path.expanduser("~"), ".cache", "huggingface")
        data_dir = os.path.join(cache_dir, "autotrain", str(random_uuid))

        if self.valid_data:
            shutil.copytree(self.train_data, os.path.join(data_dir, "train"))
            shutil.copytree(self.valid_data, os.path.join(data_dir, "validation"))

            train_metadata = self._process_metadata(os.path.join(data_dir, "train"))
            valid_metadata = self._process_metadata(os.path.join(data_dir, "validation"))

            train_metadata.to_json(os.path.join(data_dir, "train", "metadata.jsonl"), orient="records", lines=True)
            valid_metadata.to_json(
                os.path.join(data_dir, "validation", "metadata.jsonl"), orient="records", lines=True
            )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/autotrain/preprocessor/vlm.py [71:128]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        return metadata

    def __post_init__(self):
        # Check if train data path exists
        if not os.path.exists(self.train_data):
            raise ValueError(f"{self.train_data} does not exist.")

        # check if self.train_data contains at least 5 image files in jpeg, png or jpg format only
        train_image_files = [f for f in os.listdir(self.train_data) if f.endswith(ALLOWED_EXTENSIONS)]
        if len(train_image_files) < 5:
            raise ValueError(f"{self.train_data} should contain at least 5 jpeg, png or jpg files.")

        # check if self.train_data contains a metadata.jsonl file
        if "metadata.jsonl" not in os.listdir(self.train_data):
            raise ValueError(f"{self.train_data} should contain a metadata.jsonl file.")

        # Check if valid data path exists
        if self.valid_data:
            if not os.path.exists(self.valid_data):
                raise ValueError(f"{self.valid_data} does not exist.")

            # check if self.valid_data contains at least 5 image files in jpeg, png or jpg format only
            valid_image_files = [f for f in os.listdir(self.valid_data) if f.endswith(ALLOWED_EXTENSIONS)]
            if len(valid_image_files) < 5:
                raise ValueError(f"{self.valid_data} should contain at least 5 jpeg, png or jpg files.")

            # check if self.valid_data contains a metadata.jsonl file
            if "metadata.jsonl" not in os.listdir(self.valid_data):
                raise ValueError(f"{self.valid_data} should contain a metadata.jsonl file.")

    def split(self, df):
        train_df, valid_df = train_test_split(
            df,
            test_size=self.test_size,
            random_state=self.seed,
        )
        train_df = train_df.reset_index(drop=True)
        valid_df = valid_df.reset_index(drop=True)
        return train_df, valid_df

    def prepare(self):
        random_uuid = uuid.uuid4()
        cache_dir = os.environ.get("HF_HOME")
        if not cache_dir:
            cache_dir = os.path.join(os.path.expanduser("~"), ".cache", "huggingface")
        data_dir = os.path.join(cache_dir, "autotrain", str(random_uuid))

        if self.valid_data:
            shutil.copytree(self.train_data, os.path.join(data_dir, "train"))
            shutil.copytree(self.valid_data, os.path.join(data_dir, "validation"))

            train_metadata = self._process_metadata(os.path.join(data_dir, "train"))
            valid_metadata = self._process_metadata(os.path.join(data_dir, "validation"))

            train_metadata.to_json(os.path.join(data_dir, "train", "metadata.jsonl"), orient="records", lines=True)
            valid_metadata.to_json(
                os.path.join(data_dir, "validation", "metadata.jsonl"), orient="records", lines=True
            )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -