Python sample_template.SampleTemplate類代碼示例

    def delete_sample_template(self, study, user, callback):
        """Delete sample template

        Parameters
        ----------
        study : Study
            The current study object
        user : User
            The current user object
        callback : function
            The callback function to call with the results once the processing
            is done
        """
        sample_template_id = int(self.get_argument('sample_template_id'))

        try:
            SampleTemplate.delete(sample_template_id)
            msg = ("Sample template %d has been deleted from study: "
                   "<b><i>%s</i></b>" % (sample_template_id, study.title))
            msg_level = "success"
        except Exception as e:
            msg = "Couldn't remove %d sample template: %s" % (
                sample_template_id, str(e))
            msg_level = "danger"

        callback((msg, msg_level, 'study_information_tab', None, None))

    def update_sample_template(self, study, user, callback):
        """Update a sample template from the POST method

        Parameters
        ----------
        study : Study
            The current study object
        user : User
            The current user object
        callback : function
            The callback function to call with the results once the processing
            is done

        Raises
        ------
        HTTPError
            If the sample template file does not exists
        """
        # If we are on this function, the argument "sample_template" must
        # defined. If not, let tornado raise its error
        sample_template = self.get_argument('sample_template')

        # Define here the message and message level in case of success
        msg = "The sample template '%s' has been updated" % sample_template
        msg_level = "success"
        # Get the uploads folder
        _, base_fp = get_mountpoint("uploads")[0]
        # Get the path of the sample template in the uploads folder
        fp_rsp = join(base_fp, str(study.id), sample_template)

        if not exists(fp_rsp):
            # The file does not exist, fail nicely
            raise HTTPError(400, "This file doesn't exist: %s" % fp_rsp)
        try:
            with warnings.catch_warnings(record=True) as warns:
                # deleting previous uploads and inserting new one
                st = SampleTemplate(study.id)
                df = load_template_to_dataframe(fp_rsp)
                st.extend(df)
                st.update(df)
                remove(fp_rsp)

                # join all the warning messages into one. Note that this info
                # will be ignored if an exception is raised
                if warns:
                    msg = '\n'.join(set(str(w.message) for w in warns))
                    msg_level = 'warning'

        except (TypeError, QiitaDBColumnError, QiitaDBExecutionError,
                QiitaDBDuplicateError, IOError, ValueError, KeyError,
                CParserError, QiitaDBDuplicateHeaderError, QiitaDBError) as e:
            # Some error occurred while processing the sample template
            # Show the error to the user so they can fix the template
            msg = html_error_message % ('updating the sample template:',
                                        basename(fp_rsp), str(e))
            msg = convert_text_html(msg)
            msg_level = "danger"
        callback((msg, msg_level, None, None, None))

def sample_template_overview_handler_get_request(study_id, user):
    # Check if the current user has access to the sample template
    sample_template_checks(study_id, user)

    # Check if the sample template exists
    exists = SampleTemplate.exists(study_id)

    # The following information should always be provided:
    # The files that have been uploaded to the system and can be a
    # sample template file
    files = [f for _, f, _ in get_files_from_uploads_folders(study_id)
             if f.endswith(('txt', 'tsv', 'xlsx'))]
    # If there is a job associated with the sample information, the job id
    job = None
    job_info = r_client.get(SAMPLE_TEMPLATE_KEY_FORMAT % study_id)
    if job_info:
        job = loads(job_info)['job_id']

    # Specific information if it exists or not:
    data_types = []
    st_fp_id = None
    old_files = []
    num_samples = 0
    num_cols = 0
    if exists:
        # If it exists we need to provide:
        # The id of the sample template file so the user can download it and
        # the list of old filepaths
        st = SampleTemplate(study_id)
        all_st_files = st.get_filepaths()
        # The current sample template file is the first one in the list
        # (pop(0)) and we are interested only in the id ([0])
        st_fp_id = all_st_files.pop(0)[0]
        # For the old filepaths we are only interested in their basename
        old_files = [basename(fp) for _, fp in all_st_files]
        # The number of samples - this is a space efficient way of counting
        # the number of samples. Doing len(list(st.keys())) creates a list
        # that we are not using
        num_samples = sum(1 for _ in st.keys())
        # The number of columns
        num_cols = len(st.categories())
    else:
        # It doesn't exist, we also need to provide the data_types in case
        # the user uploads a QIIME mapping file
        data_types = sorted(data_types_get_req()['data_types'])

    return {'exists': exists,
            'uploaded_files': files,
            'data_types': data_types,
            'user_can_edit': Study(study_id).can_edit(user),
            'job': job,
            'download_id': st_fp_id,
            'old_files': old_files,
            'num_samples': num_samples,
            'num_columns': num_cols}

    def tearDown(self):
        for fp in self._clean_up_files:
            if exists(fp):
                remove(fp)

        study_id = self.new_study.id
        for pt in self.new_study.prep_templates():
            PrepTemplate.delete(pt.id)
        if SampleTemplate.exists(study_id):
            SampleTemplate.delete(study_id)
        Study.delete(study_id)

def create_sample_template(fp, study, is_mapping_file, data_type=None):
    """Creates a sample template

    Parameters
    ----------
    fp : str
        The file path to the template file
    study : qiita_db.study.Study
        The study to add the sample template to
    is_mapping_file : bool
        Whether `fp` contains a mapping file or a sample template
    data_type : str, optional
        If `is_mapping_file` is True, the data type of the prep template to be
        created

    Returns
    -------
    dict of {str: str}
        A dict of the form {'status': str, 'message': str}
    """
    # The imports need to be in here because this code is executed in
    # the ipython workers
    import warnings
    from os import remove
    from qiita_db.metadata_template.sample_template import SampleTemplate
    from qiita_db.metadata_template.util import load_template_to_dataframe
    from qiita_ware.metadata_pipeline import (
        create_templates_from_qiime_mapping_file)

    status = 'success'
    msg = ''
    try:
        with warnings.catch_warnings(record=True) as warns:
            if is_mapping_file:
                create_templates_from_qiime_mapping_file(fp, study,
                                                         data_type)
            else:
                SampleTemplate.create(load_template_to_dataframe(fp),
                                      study)
            remove(fp)

            # join all the warning messages into one. Note that this
            # info will be ignored if an exception is raised
            if warns:
                msg = '\n'.join(set(str(w.message) for w in warns))
                status = 'warning'
    except Exception as e:
        # Some error occurred while processing the sample template
        # Show the error to the user so they can fix the template
        status = 'danger'
        msg = str(e)

    return {'status': status, 'message': msg}

def sample_template_checks(study_id, user, check_exists=False):
    """Performs different checks and raises errors if any of the checks fail

    Parameters
    ----------
    study_id : int
        The study id
    user : qiita_db.user.User
        The user trying to access the study
    check_exists : bool, optional
        If true, check if the sample template exists

    Raises
    ------
    HTTPError
        404 if the study does not exist
        403 if the user does not have access to the study
        404 if check_exists == True and the sample template doesn't exist
    """
    try:
        study = Study(int(study_id))
    except QiitaDBUnknownIDError:
        raise HTTPError(404, reason='Study does not exist')
    if not study.has_access(user):
        raise HTTPError(403, reason='User does not have access to study')

    # Check if the sample template exists
    if check_exists and not SampleTemplate.exists(study_id):
        raise HTTPError(404, reason="Study %s doesn't have sample information"
                        % study_id)

    def display_template(self, preprocessed_data_id, msg, msg_level):
        """Simple function to avoid duplication of code"""
        preprocessed_data_id = int(preprocessed_data_id)
        try:
            preprocessed_data = Artifact(preprocessed_data_id)
        except QiitaDBUnknownIDError:
            raise HTTPError(404, "Artifact %d does not exist!" % preprocessed_data_id)
        else:
            user = self.current_user
            if user.level != "admin":
                raise HTTPError(403, "No permissions of admin, " "get/VAMPSSubmitHandler: %s!" % user.id)

        prep_template = PrepTemplate(preprocessed_data.prep_template)
        sample_template = SampleTemplate(preprocessed_data.study)
        study = Study(preprocessed_data.study)
        stats = [
            ("Number of samples", len(prep_template)),
            ("Number of metadata headers", len(sample_template.categories())),
        ]

        demux = [path for _, path, ftype in preprocessed_data.get_filepaths() if ftype == "preprocessed_demux"]
        demux_length = len(demux)

        if not demux_length:
            msg = "Study does not appear to have demultiplexed " "sequences associated"
            msg_level = "danger"
        elif demux_length > 1:
            msg = "Study appears to have multiple demultiplexed files!"
            msg_level = "danger"
        elif demux_length == 1:
            demux_file = demux[0]
            demux_file_stats = demux_stats(demux_file)
            stats.append(("Number of sequences", demux_file_stats.n))
            msg_level = "success"

        self.render(
            "vamps_submission.html",
            study_title=study.title,
            stats=stats,
            message=msg,
            study_id=study.id,
            level=msg_level,
            preprocessed_data_id=preprocessed_data_id,
        )

 def get(self, message="", msg_level=None):
     all_emails_except_current = yield Task(self._get_all_emails)
     all_emails_except_current.remove(self.current_user.id)
     avail_meta = SampleTemplate.metadata_headers() +\
         get_table_cols("study")
     self.render('list_studies.html',
                 availmeta=avail_meta,
                 all_emails_except_current=all_emails_except_current,
                 message=message,
                 msg_level=msg_level)

def update_sample_template(study_id, fp):
    """Updates a sample template

    Parameters
    ----------
    study_id : int
        Study id whose template is going to be updated
    fp : str
        The file path to the template file

    Returns
    -------
    dict of {str: str}
        A dict of the form {'status': str, 'message': str}
    """
    import warnings
    from os import remove
    from qiita_db.metadata_template.util import load_template_to_dataframe
    from qiita_db.metadata_template.sample_template import SampleTemplate

    msg = ''
    status = 'success'

    try:
        with warnings.catch_warnings(record=True) as warns:
            # deleting previous uploads and inserting new one
            st = SampleTemplate(study_id)
            df = load_template_to_dataframe(fp)
            st.extend(df)
            st.update(df)
            remove(fp)

            # join all the warning messages into one. Note that this info
            # will be ignored if an exception is raised
            if warns:
                msg = '\n'.join(set(str(w.message) for w in warns))
                status = 'warning'
    except Exception as e:
            status = 'danger'
            msg = str(e)

    return {'status': status, 'message': msg}

def sample_template_summary_get_req(study_id, user):
    """Returns a summary of the sample template metadata columns

    Parameters
    ----------
    study_id: int
        The study to retrieve the sample information summary
    user: qiita_db.user
        The user performing the request

    Returns
    -------
    dict of {str: object}
        Keys are metadata categories and the values are list of tuples. Each
        tuple is an observed value in the category and the number of times
        it's seen.

    Raises
    ------
    HTTPError
        404 If the sample template doesn't exist
    """
    # Check if the current user has access to the study and if the sample
    # template exists
    sample_template_checks(study_id, user, check_exists=True)

    st = SampleTemplate(study_id)
    df = st.to_dataframe()

    # Drop the study_id column if it exists
    if 'study_id' in df.columns:
        df.drop('study_id', axis=1, inplace=True)

    res = {}
    for column in df.columns:
        counts = df[column].value_counts()
        res[str(column)] = [(str(key), counts[key])
                            for key in natsorted(
                                counts.index,
                                key=lambda x: unicode(x, errors='ignore'))]

    return res

    def display_template(self, study, user, msg, msg_level, full_access,
                         top_tab=None, sub_tab=None, prep_tab=None):
        """Simple function to avoid duplication of code"""
        study_status = study.status
        user_level = user.level
        sample_template_exists = SampleTemplate.exists(study.id)

        if sample_template_exists:
            st = SampleTemplate(study.id)
            missing_cols = st.check_restrictions(
                [SAMPLE_TEMPLATE_COLUMNS['qiita_main']])
            allow_approval = len(missing_cols) == 0
            approval_deny_msg = (
                "Processed data approval request is disabled due to missing "
                "columns in the sample template: %s" % ', '.join(missing_cols))
        else:
            allow_approval = False
            approval_deny_msg = ""

        # The general information of the study can be changed if the study is
        # not public or if the user is an admin, in which case they can always
        # modify the information of the study
        show_edit_btn = study_status != 'public' or user_level == 'admin'

        # Make the error message suitable for html
        msg = msg.replace('\n', "<br/>")

        self.render('study_description.html',
                    message=msg,
                    level=msg_level,
                    study=study,
                    study_title=study.title,
                    study_alias=study.info['study_alias'],
                    show_edit_btn=show_edit_btn,
                    show_data_tabs=sample_template_exists,
                    full_access=full_access,
                    allow_approval=allow_approval,
                    approval_deny_msg=approval_deny_msg,
                    top_tab=top_tab,
                    sub_tab=sub_tab,
                    prep_tab=prep_tab)

    def test_get_lat_longs_EMP_portal(self):
        info = {
            'timeseries_type_id': 1,
            'lab_person_id': None,
            'principal_investigator_id': 3,
            'metadata_complete': False,
            'mixs_compliant': True,
            'study_description': 'desc',
            'study_alias': 'alias',
            'study_abstract': 'abstract'}

        study = Study.create(User('[email protected]'), 'test_study_1', efo=[1],
                             info=info)
        Portal('EMP').add_studies([study.id])

        md = {
            'my.sample': {
                'physical_specimen_location': 'location1',
                'physical_specimen_remaining': True,
                'dna_extracted': True,
                'sample_type': 'type1',
                'collection_timestamp': datetime(2014, 5, 29, 12, 24, 51),
                'host_subject_id': 'NotIdentified',
                'Description': 'Test Sample 4',
                'str_column': 'Value for sample 4',
                'int_column': 4,
                'latitude': 42.42,
                'longitude': 41.41,
                'taxon_id': 9606,
                'scientific_name': 'homo sapiens'}
        }

        md_ext = pd.DataFrame.from_dict(md, orient='index')
        SampleTemplate.create(md_ext, study)

        qiita_config.portal = 'EMP'

        obs = get_lat_longs()
        exp = [[42.42, 41.41]]

        self.assertItemsEqual(obs, exp)

    def test_delete_sample_template(self):
        # Error case
        job = self._create_job('delete_sample_template', {'study': 1})
        private_task(job.id)
        self.assertEqual(job.status, 'error')
        self.assertIn("Sample template cannot be erased because there are "
                      "prep templates associated", job.log.msg)

        # Success case
        info = {"timeseries_type_id": '1',
                "metadata_complete": 'true',
                "mixs_compliant": 'true',
                "number_samples_collected": 25,
                "number_samples_promised": 28,
                "study_alias": "TDST",
                "study_description": "Test delete sample template",
                "study_abstract": "Test delete sample template",
                "principal_investigator_id": StudyPerson(1)}
        study = Study.create(User('[email protected]'),
                             "Delete Sample Template test", info)
        metadata = pd.DataFrame.from_dict(
            {'Sample1': {'physical_specimen_location': 'location1',
                         'physical_specimen_remaining': 'true',
                         'dna_extracted': 'true',
                         'sample_type': 'type1',
                         'collection_timestamp': '2014-05-29 12:24:15',
                         'host_subject_id': 'NotIdentified',
                         'Description': 'Test Sample 1',
                         'latitude': '42.42',
                         'longitude': '41.41',
                         'taxon_id': '9606',
                         'scientific_name': 'homo sapiens'}},
            orient='index', dtype=str)
        SampleTemplate.create(metadata, study)

        job = self._create_job('delete_sample_template', {'study': study.id})
        private_task(job.id)
        self.assertEqual(job.status, 'success')
        self.assertFalse(SampleTemplate.exists(study.id))

def sample_template_filepaths_get_req(study_id, user_id):
    """Returns all the filepaths attached to the sample template

    Parameters
    ----------
    study_id : int
        The current study object id
    user_id : str
        The current user object id

    Returns
    -------
    dict
        Filepaths in the form
        {'status': status,
         'message': msg,
         'filepaths': filepaths}
        status can be success, warning, or error depending on result
        message has the warnings or errors
        filepaths is a list of tuple of int and str
        All files in the sample template, as [(id, URL), ...]
    """
    exists = _check_sample_template_exists(int(study_id))
    if exists['status'] != 'success':
        return exists
    access_error = check_access(study_id, user_id)
    if access_error:
        return access_error

    try:
        template = SampleTemplate(int(study_id))
    except QiitaDBUnknownIDError as e:
        return {'status': 'error',
                'message': str(e)}

    return {'status': 'success',
            'message': '',
            'filepaths': template.get_filepaths()
            }

def sample_template_category_get_req(category, samp_id, user_id):
    """Returns dict of values for each sample in the given category

    Parameters
    ----------
    category : str
        Metadata category to get values for
    samp_id : int or str typecastable to int
        SampleTemplate id to get info for
    user_id : str
        User requesting the sample template info

    Returns
    -------
    dict
        Returns information in the form
        {'status': str,
         'message': str,
         'values': dict of {str: object}}
    """
    exists = _check_sample_template_exists(int(samp_id))
    if exists['status'] != 'success':
        return exists
    access_error = check_access(samp_id, user_id)
    if access_error:
        return access_error

    st = SampleTemplate(int(samp_id))
    try:
        values = st.get_category(category)
    except QiitaDBColumnError:
        return {'status': 'error',
                'message': 'Category %s does not exist in sample template' %
                category}
    return {'status': 'success',
            'message': '',
            'values': values}