polly-python 2.5.0__tar.gz → 3.1.0__tar.gz

{polly_python-2.5.0/polly_python.egg-info → polly_python-3.1.0}/PKG-INFO

@@ -1,14 +1,14 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: polly_python
-Version: 2.5.0
+Version: 3.1.0
 Summary: Polly SDK
 Home-page: https://github.com/ElucidataInc/polly-python
 Project-URL: Documentation, https://docs.elucidata.io
 Project-URL: Tutorial Notebooks, https://github.com/ElucidataInc/polly-python
-Requires-Python: >3.8
+Requires-Python: <3.12,>=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
-Requires-Dist: elucidatacmapPy==3.3.4
+Requires-Dist: cmapPy<=4.0.1
 Requires-Dist: cloudpathlib>=0.15.0
 Requires-Dist: retrying==1.3.4
 Requires-Dist: rst2txt==1.1.0
@@ -17,22 +17,15 @@ Requires-Dist: mixpanel==4.10.0
 Requires-Dist: Deprecated>=1.2.12
 Requires-Dist: pytest>=6.2.5
 Requires-Dist: cryptography<=38.0.0,>=37.0.1
-Requires-Dist: plotly<5.0.0,>=4.8.1; python_version > "3.6" and python_version < "3.7"
 Requires-Dist: plotly>=5.0.0; python_version >= "3.7"
-Requires-Dist: pandas<1.2.0,>=1.1.0; python_version > "3.6" and python_version < "3.7"
-Requires-Dist: pandas>=1.3.5; python_version >= "3.7"
-Requires-Dist: pydantic<1.10.0a1,>=1.8.2; python_version > "3.6" and python_version < "3.7"
+Requires-Dist: pandas<=2.2.2,>=1.3.5; python_version >= "3.7"
+Requires-Dist: numpy<=1.26.4
 Requires-Dist: pydantic==1.10.12; python_version >= "3.7"
 Requires-Dist: requests==2.28.1
-Requires-Dist: numpy==1.26.4
-Requires-Dist: boto3<1.24.0,>=1.17.73; python_version > "3.6" and python_version < "3.7"
-Requires-Dist: boto3>=1.24.0; python_version >= "3.7"
-Requires-Dist: botocore<1.27.0,>=1.20.73; python_version > "3.6" and python_version < "3.7"
-Requires-Dist: botocore>=1.27.0; python_version >= "3.7"
-Requires-Dist: joblib<=1.1.0,>0.11.0; python_version > "3.6" and python_version < "3.7"
+Requires-Dist: boto3<2.0,>=1.24.0; python_version >= "3.7"
+Requires-Dist: botocore<2.0,>=1.27.0; python_version >= "3.7"
 Requires-Dist: joblib>=1.2.0; python_version >= "3.7"
 Requires-Dist: tabulate==0.9.0
-Requires-Dist: tqdm<4.65.0,>=4.61.0; python_version > "3.6" and python_version < "3.7"
 Requires-Dist: tqdm==4.65.0; python_version >= "3.7"
 Provides-Extra: testing
 Requires-Dist: black; extra == "testing"

polly_python-3.1.0/polly/__init__.py

@@ -0,0 +1 @@
+__version__ = "3.1.0"

{polly_python-2.5.0 → polly_python-3.1.0}/polly/constants.py

@@ -91,24 +91,6 @@ IO_CHUNKSIZE_LARGE_FILE_SIZE = 100 * MB
 # S3 Exceptions
 EXPIRED_TOKEN = "ExpiredToken"
 
-# cohort constants
-COHORT_VERSION = "0.2"
-COHORT_CONSTANTS_URL = (
-    "https://elucidatainc.github.io/PublicAssets/cohort_constants.txt"
-)
-
-OBSOLETE_METADATA_FIELDS = [
-    "package",
-    "region",
-    "bucket",
-    "key",
-    "file_type",
-    "file_location",
-    "src_uri",
-    "timestamp_",
-]
-dot = "."
-
 GETTING_UPLOAD_URLS_PAYLOAD = {"data": {"type": "files", "attributes": {"folder": ""}}}
 
 INGESTION_LEVEL_METADATA = {

{polly_python-2.5.0 → polly_python-3.1.0}/polly/curation.py

@@ -1,9 +1,8 @@
 import json
 from collections import namedtuple
-import os
-import shutil
+
 from typing import Dict, Optional, List
-import warnings
+
 import pandas as pd
 from functools import lru_cache
 from polly.errors import (
@@ -13,15 +12,15 @@ from polly.errors import (
     RequestException,
     UnauthorizedException,
     extract_json_api_error,
-    paramException,
 )
 from polly.auth import Polly
-from polly.cohort import Cohort
+
 from polly import helpers, constants as const, application_error_info as app_err_info
 from polly.help import example
 import polly.http_response_codes as http_codes
-from polly.constants import SUPPORTED_ENTITY_TYPES, CURATION_COHORT_CACHE
-from polly.helpers import get_cohort_constants
+
+from polly.constants import SUPPORTED_ENTITY_TYPES
+
 from polly.tracking import Track
 
 
@@ -48,8 +47,6 @@ class Curation:
         env="",
         default_env="polly",
     ) -> None:
-        # check if COMPUTE_ENV_VARIABLE present or not
-        # if COMPUTE_ENV_VARIABLE, give priority
         env = helpers.get_platform_value_from_env(
             const.COMPUTE_ENV_VARIABLE, default_env, env
         )
@@ -60,163 +57,12 @@ class Curation:
             f"https://api.datalake.discover.{self.session.env}.elucidata.io/elastic/v2"
         )
         self.inference_url = f"https://api.discover.{self.session.env}.elucidata.io/curations/inferences/"
-        self.cohort = Cohort()
-        self.cohort_constants = get_cohort_constants()
 
     def _handle_errors(self, response):
         detail = response.get("errors")[0].get("detail", [])
         title = response.get("errors")[0].get("title", [])
         return title, detail
 
-    def _fetch_metadata_from_cohort(self, repo_name: str, dataset_ids: List[str]):
-        """
-        Utility function for fetching metadata using cohorts.
-
-        Arguments:
-            repo_name (str) : name of the repository for fetching datasets.
-            dataset_ids (List[str]): dataset ids to be used for inference
-
-        Returns:
-            Returns sample metadata, dataset and sample ids.
-        """
-        sample_metadata = {}
-        dataset_to_sample_id = {"dataset_id": [], "sample_id": []}
-
-        if not (os.path.isdir(CURATION_COHORT_CACHE)):
-            os.mkdir(CURATION_COHORT_CACHE)
-        else:
-            shutil.rmtree(CURATION_COHORT_CACHE)
-            os.mkdir(CURATION_COHORT_CACHE)
-
-        self.cohort.create_cohort(
-            CURATION_COHORT_CACHE, "sample_metadata_query", "desc"
-        )
-
-        # Fetch metadata using cohorts
-        for dataset_id in dataset_ids:
-            datasets_sample_metadata = []
-
-            if not (
-                repo_name in self.cohort_constants
-                and self.cohort_constants[repo_name]["file_structure"] != "multiple"
-            ):
-                # multiple mapped repo such as GEO
-                self.cohort.add_to_cohort(repo_name, dataset_id=dataset_id)
-            else:
-                # for single mapped repos such as TCGA
-                self.cohort.add_to_cohort(repo_name, dataset_id=[dataset_id])
-
-            col_metadata = self.cohort.merge_data("sample")
-            all_sample_ids = col_metadata.index.tolist()
-
-            col_metadata.loc[:, "dataset_id"] = dataset_id
-            dataset_to_sample_id["dataset_id"] += [dataset_id] * len(all_sample_ids)
-
-            col_metadata.loc[:, "sample_id"] = all_sample_ids
-            dataset_to_sample_id["sample_id"] += all_sample_ids
-
-            datasets_sample_metadata += list(col_metadata.T.to_dict().values())
-
-            if not (
-                repo_name in self.cohort_constants
-                and self.cohort_constants[repo_name]["file_structure"] != "multiple"
-            ):
-                self.cohort.remove_from_cohort(dataset_id)
-            else:
-                self.cohort.remove_from_cohort([dataset_id])
-
-            sample_metadata[dataset_id] = datasets_sample_metadata
-
-        dataset_to_sample_id = pd.DataFrame.from_dict(dataset_to_sample_id)
-
-        return sample_metadata, dataset_to_sample_id
-
-    def _clinical_model_param_checks(
-        self,
-        repo_name: str,
-        dataset_ids: List[str],
-        sample_ids: Optional[List[str]] = None,
-    ):
-        """
-        Checking the parameter passed to the clinical label assigning model.
-
-        Arguments:
-            repo_name (str): repo name
-            dataset_ids (list[str]): list of dataset ids
-
-        Keyword Arguments:
-            sample_ids (list[str], optional): Optional Parameter. List of sample ids.
-            Default is 'None'.
-
-        Raises:
-            paramException
-        """
-        if dataset_ids is None or type(dataset_ids) is not list:
-            raise paramException(
-                title="Param Exception",
-                detail="Dataset IDs should be given as a valid list of strings",
-            )
-
-        if sample_ids is not None and type(sample_ids) is not list:
-            raise paramException(
-                title="Param Exception",
-                detail="Sample IDs should be given as a valid list of strings",
-            )
-
-        if repo_name != "geo" and not any(
-            ["GSE" in dataset_id for dataset_id in dataset_ids]
-        ):
-            warnings.warn(
-                "The model is tested with GEO metadata and the labels may be wrong for other repos"
-            )
-
-    def _post_process_clinical_tags(
-        self,
-        clinical_tags: pd.DataFrame,
-        is_sample_tag: bool,
-        sample_ids: Optional[List[str]] = None,
-    ) -> pd.DataFrame:
-        """
-        process the response of the model (dataframe with clinical tags and samples)
-        and return relevant feilds.
-        incase no sample_ids are provided by the user, we return the dataset_ids and the clinical tags
-        incase sample_ids are also provided, then we return the dataset_ids, the sample_ids and the clincal tags.
-
-        Arguments:
-            clinical_tags (pd.DataFrame): dataframe of the sample_ids and assigned clinical tags
-            is_sample_tag (bool): if samples passed
-
-        Keyword Arguments:
-            sample_ids (list[str]): list of sample ids (default: {None})
-
-        Returns:
-            a dataframe with the the dataset_ids, sample_ids and the assigned clinical tags
-        """
-        if is_sample_tag:
-            # if the user has provided list of samples, then we filter in just those sample ids
-            # for the dataset ids.
-            # taking only those clinical tags and samples where the sample_ids are in the sample_id list
-            # provided by the user.
-            clinical_tags = clinical_tags[
-                clinical_tags["sample_id"].isin(sample_ids)
-            ].reset_index(drop=True)
-
-            # in case the sample_ids provided by the user are not present in the dataset_ids provided.
-            if clinical_tags.empty or clinical_tags.shape[0] < len(sample_ids):
-                warnings.warn(
-                    "The output is empty or has missing sample ids because they are not present in given datasets."
-                )
-
-            # return sample level tags here
-            return clinical_tags
-        # if no sample_ids were passed by the user, then
-        # returning dataset level tags by removing sample id and removing duplicate columns
-        return (
-            clinical_tags.drop(columns=["sample_id"])
-            .drop_duplicates()
-            .reset_index(drop=True)
-        )
-
     def _handle_perform_inference_api_error(self, response):
         if response.status_code == http_codes.UNAUTHORIZED:
             raise UnauthorizedException("User is unauthorized to access this")
@@ -482,84 +328,3 @@ class Curation:
         sample_metadata["is_control"] = output["is_control"].values
         sample_metadata["control_prob"] = output["control_prob"].values
         return sample_metadata
-
-    @Track.track_decorator
-    def assign_clinical_labels(
-        self,
-        repo_name: str,
-        dataset_ids: List[str],
-        sample_ids: Optional[List[str]] = None,
-    ) -> pd.DataFrame:
-        """
-        Returns a list of clinical or non clinical labels for the given datasets or samples.
-
-        Arguments:
-            repo_name (str): name of the repository for fetching datasets.
-            dataset_ids (List[str]): dataset ids to be used for inference
-
-        Keyword Arguments:
-            sample_ids (List[str], optional): Optional Parameter. Sample ids if that is needed.
-
-        Raises:
-            RequestException: API response exception
-            ParamException: Invalid parameters
-            err
-
-        Returns:
-            dataframe which is a list of clinical tags for given ids
-        """
-        warnings.formatwarning = lambda msg, *args, **kwargs: f"WARNING: {msg}\n"
-
-        try:
-            self._clinical_model_param_checks(repo_name, dataset_ids, sample_ids)
-            # evaluating the inference level based on if the user has provided sample_ids
-            is_sample_tag = sample_ids is not None
-            inference_level = "sample_id" if (is_sample_tag) else "dataset_id"
-
-            sample_metadata, dataset_to_sample_id = self._fetch_metadata_from_cohort(
-                repo_name=repo_name, dataset_ids=dataset_ids
-            )
-
-            clinical_model_predictions = []
-
-            for dataset_id in sample_metadata:
-                # Get output from model endpoint and structure output
-                payload = {
-                    "sample_metadata": sample_metadata[dataset_id],
-                    "sample_id_column": "sample_id",
-                    "dataset_id_column": "dataset_id",
-                    "is_sample_tag": is_sample_tag,
-                }
-
-                output = self._perform_inference("clinical-classifier", payload)
-                if "errors" in output:
-                    title, detail = self._handle_errors(output)
-                    raise RequestException(title, detail)
-
-                output = output["clinical_predictions"]
-
-                clinical_model_predictions += output
-
-            # creating dataframe with inference_level and clinical_tags with values from the clinical_model_predictions
-            clinical_tags = pd.DataFrame(
-                {
-                    inference_level: [
-                        tag["tag_id"] for tag in clinical_model_predictions
-                    ],
-                    "clinical_tag": [
-                        tag["clinical_tag"] for tag in clinical_model_predictions
-                    ],
-                }
-            )
-
-            clinical_tags = pd.merge(
-                dataset_to_sample_id, clinical_tags, on=inference_level
-            )
-
-            clinical_tags = self._post_process_clinical_tags(
-                clinical_tags, is_sample_tag, sample_ids
-            )
-        except Exception as err:
-            raise err
-
-        return clinical_tags

{polly_python-2.5.0 → polly_python-3.1.0}/polly/errors.py

@@ -97,68 +97,6 @@ class InvalidDirectoryPathException(Exception):
         return "This path does not represent an existing directory. Please try again."
 
 
-class InvalidCohortPathException(Exception):
-    def __str__(self):
-        return "This path does not represent a Cohort. Please try again."
-
-
-class InvalidCohortNameException(Exception):
-    def __str__(self, cohort_name):
-        return f"The identifier {cohort_name} does not represent a valid cohort name. Please try again."
-
-
-class InvalidRepoException(Exception):
-    def __init__(self, repo_name):
-        self.repo_name = repo_name
-
-    def __str__(self):
-        return f"The repository : {self.repo_name} is not supported. Please contact Polly Support."
-
-
-class InvalidDatasetException(Exception):
-    def __str__(self):
-        return "Dataset/s not added."
-
-
-class InvalidCohortOperationException(Exception):
-    def __str__(self):
-        return "This operation is not valid as no cohort has been instantiated."
-
-
-class EmptyCohortException(Exception):
-    def __str__(self):
-        return "There are no datasets in the cohort. Please try adding datasets using add_to_cohort() function."
-
-
-class CohortEditException(Exception):
-    def __str__(self):
-        return "No parameter specified for editing in cohort"
-
-
-class InvalidCohortMergeOperation(Exception):
-    def __str__(self):
-        return "Incorrect or blank parameter specified for merging in cohort"
-
-
-class InvalidCohortAddition(Exception):
-    def __str__(self):
-        return "The repository type is not compatible with the cohort due to different file structure. Please try again."
-
-
-class OutdatedCohortVersion(Exception):
-    def __init__(self, version):
-        self.version = version
-
-    def __str__(self):
-        return f"The Cohort version is outdated. Please try again with the new version VERSION-{self.version}."
-
-
-class TechnicalFaultException(Exception):
-    def __str__(self):
-        return "Samples not downloaded due to a technical fault. Please check \
-the arguments passed and try again. Contact Polly Support in case of repeated failure."
-
-
 class RequestFailureException(Exception):
     def __str__(self):
         return "Sorry, we're unable to fetch the metadata now. Please contact polly.support@elucidata.io"

{polly_python-2.5.0 → polly_python-3.1.0}/polly/help.py

@@ -179,7 +179,7 @@ def checkclass(cls) -> None:
         print("Note : use class to get help")
         raise TypeError(title="Use class")
 
-    if cls.__name__ not in ["Polly", "OmixAtlas", "Cohort", "Workspaces"]:
+    if cls.__name__ not in ["Polly", "OmixAtlas", "Workspaces"]:
         print("Other class methods not allowed")
         raise Exception(title="Other class are not allowed")
 
@@ -210,7 +210,6 @@ def get_line(fun: str, kind: str, txt: str, function_name: str, cls, doc: bool)
     # function will return lines to print
     # for a function or class
     Link = {
-        "cohort": "https://github.com/ElucidataInc/PublicAssets/blob/master/polly-python/example/cohort.ipynb",
         "omixatlas": "https://github.com/ElucidataInc/PublicAssets/blob/master/polly-python/example/omixatlas.ipynb",
         "polly": "https://github.com/ElucidataInc/PublicAssets/blob/master/polly-python/example/polly.ipynb",
         "workspaces": "https://github.com/ElucidataInc/PublicAssets/blob/master/polly-python/example/workspaces.ipynb",
@@ -301,7 +300,7 @@ def get_txt(
 
 def example(cls, function_name: str = "") -> None:
     """
-    function to see examples for class - Polly, OmixAtlas, Workspaces, Cohort and it's member funtions
+    function to see examples for class - Polly, OmixAtlas, Workspaces and it's member funtions
 
     ``Args:``
         ``function_name (optional) str:`` provide function name to see examples default empty.

{polly_python-2.5.0 → polly_python-3.1.0}/polly/helpers.py

@@ -1,7 +1,8 @@
 import os
 import re
 import json
-import logging
+
+# import logging
 import requests
 import urllib.request
 from cloudpathlib import S3Client
@@ -16,16 +17,14 @@ from polly.errors import (
     OperationFailedException,
     paramException,
     AccessDeniedError,
-    InvalidRepoException,
     DatatypeNotFoundException,
     RepositoryNotFoundException,
 )
-from polly.constants import COHORT_CONSTANTS_URL
-import contextlib
-import joblib
+
 import urllib
 import pandas as pd
-import polly.http_response_codes as http_codes
+
+# import polly.http_response_codes as http_codes
 from polly.tracking import Track
 import polly.constants as const
 import string
@@ -411,43 +410,6 @@ def elastic_query(index_name: str, dataset_id: str) -> dict:
     return query
 
 
-def get_cohort_constants() -> json:
-    """
-    Returns cohort info from public assests url
-    """
-    response = requests.get(COHORT_CONSTANTS_URL)
-    error_handler(response)
-    return json.loads(response.text)
-
-
-def validate_datatype(datatype: str):
-    """
-    Function to validate datatype of a dataset
-    Returns 1 in case of datatype is Single Cell, 0 otherwise
-    """
-    if datatype == "Single cell":
-        return 1
-    return 0
-
-
-@contextlib.contextmanager
-def tqdm_joblib(tqdm_object):
-    """Context manager to patch joblib to report into tqdm progress bar given as argument"""
-
-    class TqdmBatchCompletionCallback(joblib.parallel.BatchCompletionCallBack):
-        def __call__(self, *args, **kwargs):
-            tqdm_object.update(n=self.batch_size)
-            return super().__call__(*args, **kwargs)
-
-    old_batch_callback = joblib.parallel.BatchCompletionCallBack
-    joblib.parallel.BatchCompletionCallBack = TqdmBatchCompletionCallback
-    try:
-        yield tqdm_object
-    finally:
-        joblib.parallel.BatchCompletionCallBack = old_batch_callback
-        tqdm_object.close()
-
-
 def check_empty(x):
     """
     Function to validate if the entry is an empty list or not.
@@ -593,21 +555,6 @@ def workspaces_permission_check(self, workspace_id) -> bool:
         )
 
 
-def return_entity_type(data_source: str, cohort_info: json) -> str:
-    """
-    Function to return entity type based on the cohort info present in public assets
-    """
-    if data_source not in cohort_info:
-        raise InvalidRepoException(data_source)
-    for repo, dict in cohort_info.items():
-        if data_source == repo:
-            if dict["file_structure"] == "single":
-                entity_type = "dataset"
-            elif dict["file_structure"] == "multiple":
-                entity_type = "sample"
-    return entity_type
-
-
 def get_files_in_dir(path_to_dir: str) -> list:
     """
     returns the files in a given directory
@@ -722,35 +669,6 @@ def replace_original_name_field(
     return replaced_metadata
 
 
-def upload_html_file(
-    session, workspace_id: int, workspace_path: str, local_report_path: str
-):
-    """
-    Function to upload an html file to a workspace.
-    """
-    upload_url = f"https://v2.api.{session.env}.elucidata.io/workspaces/{workspace_id}/upload_url"
-    params = {"file_path": workspace_path, "content_type": "text/html"}
-    # get request to get the signed url for s3
-    response = session.get(upload_url, params=params)
-    error_handler(response)
-    attributes = response.json().get("data").get("attributes")
-    try:
-        with open(local_report_path, "rb") as file_to_upload:
-            # uploading the local file to the signed url
-            files = {"file": (local_report_path, file_to_upload)}
-            upload_response = requests.post(
-                attributes["url"], data=attributes["fields"], files=files
-            )
-            error_handler(upload_response)
-            if upload_response.status_code == http_codes.CREATED:
-                logging.basicConfig(level=logging.INFO)
-                logging.info(
-                    f"File uploaded successfully to workspace-id = {workspace_id} at path = {workspace_path}!"
-                )
-    except Exception as e:
-        raise e
-
-
 def get_folder_list_from_list_of_filepaths(filenames_fullpath_list: list) -> list:
     """
     gives back only the folders from a list of filepaths provided.