clarifai 10.2.1__py3-none-any.whl → 10.3.0__py3-none-any.whl

clarifai/client/user.py

@@ -7,7 +7,6 @@ from google.protobuf.json_format import MessageToDict
 from clarifai.client.app import App
 from clarifai.client.base import BaseClient
 from clarifai.client.lister import Lister
-from clarifai.client.runner import Runner
 from clarifai.errors import UserError
 from clarifai.utils.logging import get_logger
 
@@ -20,6 +19,7 @@ class User(Lister, BaseClient):
                base_url: str = "https://api.clarifai.com",
                pat: str = None,
                token: str = None,
+               root_certificates_path: str = None,
                **kwargs):
     """Initializes an User object.
 
@@ -28,12 +28,20 @@ class User(Lister, BaseClient):
         base_url (str): Base API url. Default "https://api.clarifai.com"
         pat (str): A personal access token for authentication. Can be set as env var CLARIFAI_PAT
         token (str): A session token for authentication. Accepts either a session token or a pat. Can be set as env var CLARIFAI_SESSION_TOKEN
+        root_certificates_path (str): Path to the SSL root certificates file, used to establish secure gRPC connections.
         **kwargs: Additional keyword arguments to be passed to the User.
     """
     self.kwargs = {**kwargs, 'id': user_id}
     self.user_info = resources_pb2.User(**self.kwargs)
     self.logger = get_logger(logger_level="INFO", name=__name__)
-    BaseClient.__init__(self, user_id=self.id, app_id="", base=base_url, pat=pat, token=token)
+    BaseClient.__init__(
+        self,
+        user_id=self.id,
+        app_id="",
+        base=base_url,
+        pat=pat,
+        token=token,
+        root_certificates_path=root_certificates_path)
     Lister.__init__(self)
 
   def list_apps(self, filter_by: Dict[str, Any] = {}, page_no: int = None,
@@ -69,7 +77,7 @@ class User(Lister, BaseClient):
           **app_info)  #(base_url=self.base, pat=self.pat, token=self.token, **app_info)
 
   def list_runners(self, filter_by: Dict[str, Any] = {}, page_no: int = None,
-                   per_page: int = None) -> Generator[Runner, None, None]:
+                   per_page: int = None) -> Generator[dict, None, None]:
     """List all runners for the user
 
     Args:
@@ -78,7 +86,7 @@ class User(Lister, BaseClient):
         per_page (int): The number of items per page.
 
     Yields:
-        Runner: Runner objects for the runners.
+        Dict: Dictionaries containing information about the runners.
 
     Example:
         >>> from clarifai.client.user import User
@@ -98,8 +106,7 @@ class User(Lister, BaseClient):
         page_no=page_no)
 
     for runner_info in all_runners_info:
-      yield Runner.from_auth_helper(
-          auth=self.auth_helper, check_runner_exists=False, **runner_info)
+      yield dict(auth=self.auth_helper, check_runner_exists=False, **runner_info)
 
   def create_app(self, app_id: str, base_workflow: str = 'Empty', **kwargs) -> App:
     """Creates an app for the user.
@@ -127,7 +134,7 @@ class User(Lister, BaseClient):
     self.logger.info("\nApp created\n%s", response.status)
     return App.from_auth_helper(auth=self.auth_helper, app_id=app_id)
 
-  def create_runner(self, runner_id: str, labels: List[str], description: str) -> Runner:
+  def create_runner(self, runner_id: str, labels: List[str], description: str) -> dict:
     """Create a runner
 
     Args:
@@ -136,13 +143,14 @@ class User(Lister, BaseClient):
       description (str): Description of Runner
 
     Returns:
-      Runner: A runner object for the specified Runner ID
+      Dict: A dictionary containing information about the specified Runner ID.
 
     Example:
         >>> from clarifai.client.user import User
         >>> client = User(user_id="user_id")
-        >>> runner = client.create_runner(runner_id="runner_id", labels=["label to link runner"], description="laptop runner")
+        >>> runner_info = client.create_runner(runner_id="runner_id", labels=["label to link runner"], description="laptop runner")
     """
+
     if not isinstance(labels, List):
       raise UserError("Labels must be a List of strings")
 
@@ -155,7 +163,7 @@ class User(Lister, BaseClient):
       raise Exception(response.status)
     self.logger.info("\nRunner created\n%s", response.status)
 
-    return Runner.from_auth_helper(
+    return dict(
         auth=self.auth_helper,
         runner_id=runner_id,
         user_id=self.id,
@@ -186,19 +194,19 @@ class User(Lister, BaseClient):
     kwargs['user_id'] = self.id
     return App.from_auth_helper(auth=self.auth_helper, app_id=app_id, **kwargs)
 
-  def runner(self, runner_id: str) -> Runner:
+  def runner(self, runner_id: str) -> dict:
     """Returns a Runner object if exists.
 
     Args:
         runner_id (str): The runner ID to interact with
 
     Returns:
-        Runner: A Runner object for the existing runner ID.
+        Dict: A dictionary containing information about the existing runner ID.
 
     Example:
         >>> from clarifai.client.user import User
         >>> client = User(user_id="user_id")
-        >>> runner = client.runner(runner_id="runner_id")
+        >>> runner_info = client.runner(runner_id="runner_id")
     """
     request = service_pb2.GetRunnerRequest(user_app_id=self.user_app_id, runner_id=runner_id)
     response = self._grpc_request(self.STUB.GetRunner, request)
@@ -212,7 +220,7 @@ class User(Lister, BaseClient):
     kwargs = self.process_response_keys(dict_response[list(dict_response.keys())[1]],
                                         list(dict_response.keys())[1])
 
-    return Runner.from_auth_helper(self.auth_helper, check_runner_exists=False, **kwargs)
+    return dict(self.auth_helper, check_runner_exists=False, **kwargs)
 
   def delete_app(self, app_id: str) -> None:
     """Deletes an app for the user.

clarifai/client/workflow.py

@@ -28,6 +28,7 @@ class Workflow(Lister, BaseClient):
                base_url: str = "https://api.clarifai.com",
                pat: str = None,
                token: str = None,
+               root_certificates_path: str = None,
                **kwargs):
     """Initializes a Workflow object.
 
@@ -43,6 +44,7 @@ class Workflow(Lister, BaseClient):
         base_url (str): Base API url. Default "https://api.clarifai.com"
         pat (str): A personal access token for authentication. Can be set as env var CLARIFAI_PAT
         token (str): A session token for authentication. Accepts either a session token or a pat. Can be set as env var CLARIFAI_SESSION_TOKEN
+        root_certificates_path (str): Path to the SSL root certificates file, used to establish secure gRPC connections.
         **kwargs: Additional keyword arguments to be passed to the Workflow.
     """
     if url and workflow_id:
@@ -59,7 +61,13 @@ class Workflow(Lister, BaseClient):
     self.workflow_info = resources_pb2.Workflow(**self.kwargs)
     self.logger = get_logger(logger_level="INFO", name=__name__)
     BaseClient.__init__(
-        self, user_id=self.user_id, app_id=self.app_id, base=base_url, pat=pat, token=token)
+        self,
+        user_id=self.user_id,
+        app_id=self.app_id,
+        base=base_url,
+        pat=pat,
+        token=token,
+        root_certificates_path=root_certificates_path)
     Lister.__init__(self)
 
   def predict(self, inputs: List[Input], workflow_state_id: str = None):

clarifai/constants/input.py

@@ -0,0 +1 @@
+MAX_UPLOAD_BATCH_SIZE = 128

clarifai/utils/evaluation/__init__.py

@@ -1,427 +1,3 @@
-import os
-from enum import Enum
-from typing import List, Tuple, Union
+from .main import EvalResultCompare
 
-from clarifai.client.dataset import Dataset
-from clarifai.client.model import Model
-
-from .helpers import (MACRO_AVG, EvalType, _BaseEvalResultHandler, get_eval_type,
-                      make_handler_by_type)
-
-try:
-  import seaborn as sns
-except ImportError:
-  raise ImportError("Can not import seaborn. Please run `pip install seaborn` to install it")
-
-try:
-  import matplotlib.pyplot as plt
-except ImportError:
-  raise ImportError("Can not import matplotlib. Please run `pip install matplotlib` to install it")
-
-try:
-  import pandas as pd
-except ImportError:
-  raise ImportError("Can not import pandas. Please run `pip install pandas` to install it")
-
-try:
-  from loguru import logger
-except ImportError:
-  from ..logging import get_logger
-  logger = get_logger(logger_level="INFO", name=__name__)
-
-__all__ = ['EvalResultCompare']
-
-
-class CompareMode(Enum):
-  MANY_MODELS_TO_ONE_DATA = 0
-  ONE_MODEL_TO_MANY_DATA = 1
-
-
-class EvalResultCompare:
-  """Compare evaluation result of models against datasets.
-  Note: The module will pick latest result on the datasets.
-  and models must be same model type
-
-  Args:
-  ---
-    models (Union[List[Model], List[str]]): List of Model or urls of models.
-    datasets (Union[Dataset, List[Dataset], str, List[str]]): A single or List of Url or Dataset
-    attempt_evaluate (bool): Evaluate when model is not evaluated with the datasets.
-    auth_kwargs (dict): Additional auth keyword arguments to be passed to the Dataset and Model if using url(s)
-  """
-
-  def __init__(self,
-               models: Union[List[Model], List[str]],
-               datasets: Union[Dataset, List[Dataset], str, List[str]],
-               attempt_evaluate: bool = False,
-               auth_kwargs: dict = {}):
-    assert isinstance(models, list), ValueError("Expected list")
-
-    if len(models) > 1:
-      self.mode = CompareMode.MANY_MODELS_TO_ONE_DATA
-      self.comparator = "Model"
-      assert isinstance(datasets, Dataset) or (
-          isinstance(datasets, list) and len(datasets) == 1
-      ), f"When comparing multiple models, must provide only one `datasets`. However got {datasets}"
-    else:
-      self.mode = CompareMode.ONE_MODEL_TO_MANY_DATA
-      self.comparator = "Dataset"
-
-    # validate models
-    if all(map(lambda x: isinstance(x, str), models)):
-      models = [Model(each, **auth_kwargs) for each in models]
-    elif not all(map(lambda x: isinstance(x, Model), models)):
-      raise ValueError(
-          f"Expected all models are list of string or list of Model, got {[type(each) for each in models]}"
-      )
-    # validate datasets
-    if not isinstance(datasets, list):
-      datasets = [
-          datasets,
-      ]
-    if all(map(lambda x: isinstance(x, str), datasets)):
-      datasets = [Dataset(each, **auth_kwargs) for each in datasets]
-    elif not all(map(lambda x: isinstance(x, Dataset), datasets)):
-      raise ValueError(
-          f"Expected datasets must be str, list of string or Dataset, list of Dataset, got {[type(each) for each in datasets]}"
-      )
-    # Validate models vs datasets together
-    self._eval_handlers: List[_BaseEvalResultHandler] = []
-    self.model_type = None
-    logger.info("Initializing models...")
-    for model in models:
-      model.load_info()
-      model_type = model.model_info.model_type_id
-      if not self.model_type:
-        self.model_type = model_type
-      else:
-        assert self.model_type == model_type, f"Can not compare when model types are different, {self.model_type} != {model_type}"
-      m = make_handler_by_type(model_type)(model=model)
-      logger.info(f"* {m.get_model_name(pretify=True)}")
-      m.find_eval_id(datasets=datasets, attempt_evaluate=attempt_evaluate)
-      self._eval_handlers.append(m)
-
-  @property
-  def eval_handlers(self):
-    return self._eval_handlers
-
-  def _loop_eval_handlers(self, func_name: str, **kwargs) -> Tuple[list, list]:
-    """ Run methods of `eval_handlers[...].model`
-
-    Args:
-      func_name (str): method name, see `_BaseEvalResultHandler` child classes
-      kwargs: keyword arguments of the method
-
-    Return:
-      tuple:
-        - list of outputs
-        - list of comparator names
-
-    """
-    outs = []
-    comparators = []
-    logger.info(f'Running `{func_name}`')
-    for _, each in enumerate(self.eval_handlers):
-      for ds_index, _ in enumerate(each.eval_data):
-        func = eval(f'each.{func_name}')
-        out = func(index=ds_index, **kwargs)
-
-        if self.mode == CompareMode.MANY_MODELS_TO_ONE_DATA:
-          name = each.get_model_name(pretify=True)
-        else:
-          name = each.get_dataset_name_by_index(ds_index, pretify=True)
-        if out is None:
-          logger.warning(f'{self.comparator}:{name} does not have valid data for `{func_name}`')
-          continue
-        comparators.append(name)
-        outs.append(out)
-
-    # remove app_id if models a
-    if self.mode == CompareMode.MANY_MODELS_TO_ONE_DATA:
-      apps = set([comp.split('/')[0] for comp in comparators])
-      if len(apps) == 1:
-        comparators = ['/'.join(comp.split('/')[1:]) for comp in comparators]
-
-    if not outs:
-      logger.warning(f'Model type {self.model_type} does not support `{func_name}`')
-
-    return outs, comparators
-
-  def detailed_summary(self,
-                       confidence_threshold: float = .5,
-                       iou_threshold: float = .5,
-                       area: str = "all",
-                       bypass_const=False) -> Union[Tuple[pd.DataFrame, pd.DataFrame], None]:
-    """
-    Retrieve and compute popular metrics of model.
-
-    Args:
-      confidence_threshold (float): confidence threshold, applicable for classification and detection. Default is 0.5
-      iou_threshold (float): iou threshold, support in range(0.5, 1., step=0.1) applicable for detection
-      area (float): size of area, support {all, small, medium}, applicable for detection
-
-    Return:
-      None or tuple of dataframe: df summary per concept and total concepts
-
-    """
-    df = []
-    total = []
-    # loop over all eval_handlers/dataset and call its method
-    outs, comparators = self._loop_eval_handlers(
-        'detailed_summary',
-        confidence_threshold=confidence_threshold,
-        iou_threshold=iou_threshold,
-        area=area,
-        bypass_const=bypass_const)
-    for indx, out in enumerate(outs):
-      _df, _total = out
-      _df[self.comparator] = [comparators[indx] for _ in range(len(_df))]
-      _total['Concept'].replace(
-          to_replace=['Total'], value=f'{self.comparator}:{comparators[indx]}', inplace=True)
-      _total.rename({'Concept': 'Total Concept'}, axis=1, inplace=True)
-      df.append(_df)
-      total.append(_total)
-
-    if df:
-      df = pd.concat(df, axis=0)
-      total = pd.concat(total, axis=0)
-      return df, total
-    else:
-      return None
-
-  def confusion_matrix(self, show=True, save_path: str = None,
-                       cm_kwargs: dict = {}) -> Union[pd.DataFrame, None]:
-    """Return dataframe of confusion matrix
-    Args:
-        show (bool, optional): Show the chart. Defaults to True.
-        save_path (str): path to save rendered chart.
-        cm_kwargs (dict): keyword args of `eval_handler[...].model.cm_kwargs` method.
-    Returns:
-        None or pd.Dataframe, If models don't have confusion matrix, return None
-    """
-    outs, comparators = self._loop_eval_handlers("confusion_matrix", **cm_kwargs)
-    all_dfs = []
-    for _, (df, anchor) in enumerate(zip(outs, comparators)):
-      df[self.comparator] = [anchor for _ in range(len(df))]
-      all_dfs.append(df)
-
-    if all_dfs:
-      all_dfs = pd.concat(all_dfs, axis=0)
-      if save_path or show:
-
-        def _facet_heatmap(data, **kws):
-          data = data.dropna(axis=1)
-          data = data.drop(self.comparator, axis=1)
-          concepts = data.columns
-          colnames = pd.MultiIndex.from_arrays([concepts], names=['Predicted'])
-          data.columns = colnames
-          ax = sns.heatmap(data, cmap='Blues', annot=True, annot_kws={"fontsize": 8}, **kws)
-          ax.set_xticklabels(ax.get_xticklabels(), rotation=45, fontsize=6)
-          ax.set_yticklabels(ax.get_yticklabels(), fontsize=6, rotation=0)
-
-        temp = all_dfs.copy()
-        temp.columns = ["_".join(pair) for pair in temp.columns]
-        with sns.plotting_context(font_scale=5.5):
-          g = sns.FacetGrid(
-              temp,
-              col=self.comparator,
-              col_wrap=3,
-              aspect=1,
-              height=3,
-              sharex=False,
-              sharey=False,
-          )
-          cbar_ax = g.figure.add_axes([.92, .3, .02, .4])
-          g = g.map_dataframe(
-              _facet_heatmap, cbar_ax=cbar_ax, vmin=0, vmax=1, cbar=True, square=True)
-          g.set_titles(col_template=str(self.comparator) + ':{col_name}', fontsize=5)
-          if show:
-            plt.show()
-          if save_path:
-            g.savefig(save_path)
-
-    return all_dfs if isinstance(all_dfs, pd.DataFrame) else None
-
-  @staticmethod
-  def _set_default_kwargs(kwargs: dict, var_name: str, value):
-    if var_name not in kwargs:
-      kwargs.update({var_name: value})
-    return kwargs
-
-  @staticmethod
-  def _setup_default_lineplot(df: pd.DataFrame, kwargs: dict):
-    hue_order = df["concept"].unique().tolist()
-    hue_order.remove(MACRO_AVG)
-    hue_order.insert(0, MACRO_AVG)
-    EvalResultCompare._set_default_kwargs(kwargs, "hue_order", hue_order)
-
-    sizes = {}
-    for each in hue_order:
-      s = 1.5
-      if each == MACRO_AVG:
-        s = 4.
-      sizes.update({each: s})
-    EvalResultCompare._set_default_kwargs(kwargs, "sizes", sizes)
-    EvalResultCompare._set_default_kwargs(kwargs, "size", "concept")
-
-    EvalResultCompare._set_default_kwargs(kwargs, "errorbar", None)
-    EvalResultCompare._set_default_kwargs(kwargs, "height", 5)
-
-    return kwargs
-
-  def roc_curve_plot(self,
-                     show=True,
-                     save_path: str = None,
-                     roc_curve_kwargs: dict = {},
-                     relplot_kwargs: dict = {}) -> Union[pd.DataFrame, None]:
-    """Return dataframe of ROC curve
-    Args:
-        show (bool, optional): Show the chart. Defaults to True.
-        save_path (str): path to save rendered chart.
-        pr_curve_kwargs (dict): keyword args of `eval_handler[...].model.roc_curve` method.
-        relplot_kwargs (dict): keyword args of `sns.relplot` except {data,x,y,hue,kind,col}. where x="fpr", y="tpr", hue="concept"
-    Returns:
-        None or pd.Dataframe, If models don't have ROC curve, return None
-    """
-    sns.set_palette("Paired")
-    outs, comparator = self._loop_eval_handlers("roc_curve", **roc_curve_kwargs)
-    all_dfs = []
-    for _, (df, anchor) in enumerate(zip(outs, comparator)):
-      df[self.comparator] = [anchor for _ in range(len(df))]
-      all_dfs.append(df)
-
-    if all_dfs:
-      all_dfs = pd.concat(all_dfs, axis=0)
-      if save_path or show:
-        relplot_kwargs = self._setup_default_lineplot(all_dfs, relplot_kwargs)
-        g = sns.relplot(
-            data=all_dfs,
-            x="fpr",
-            y="tpr",
-            hue='concept',
-            kind="line",
-            col=self.comparator,
-            **relplot_kwargs)
-        g.set_titles(col_template=str(self.comparator) + ':{col_name}', fontsize=5)
-        if show:
-          plt.show()
-        if save_path:
-          g.savefig(save_path)
-
-    return all_dfs if isinstance(all_dfs, pd.DataFrame) else None
-
-  def pr_plot(self,
-              show=True,
-              save_path: str = None,
-              pr_curve_kwargs: dict = {},
-              relplot_kwargs: dict = {}) -> Union[pd.DataFrame, None]:
-    """Return dataframe of PR curve
-    Args:
-        show (bool, optional): Show the chart. Defaults to True.
-        save_path (str): path to save rendered chart.
-        pr_curve_kwargs (dict): keyword args of `eval_handler[...].model.pr_curve` method.
-        relplot_kwargs (dict): keyword args of `sns.relplot` except {data,x,y,hue,kind,col} where x="recall", y="precision", hue="concept"
-    Returns:
-        None or pd.Dataframe, If models don't have PR curve, return None
-    """
-    sns.set_palette("Paired")
-    outs, comparator = self._loop_eval_handlers("pr_curve", **pr_curve_kwargs)
-    all_dfs = []
-    for _, (df, anchor) in enumerate(zip(outs, comparator)):
-      df[self.comparator] = [anchor for _ in range(len(df))]
-      all_dfs.append(df)
-
-    if all_dfs:
-      all_dfs = pd.concat(all_dfs, axis=0)
-      if save_path or show:
-        relplot_kwargs = self._setup_default_lineplot(all_dfs, relplot_kwargs)
-        g = sns.relplot(
-            data=all_dfs,
-            x="recall",
-            y="precision",
-            hue='concept',
-            kind="line",
-            col=self.comparator,
-            **relplot_kwargs)
-        g.set_titles(col_template=str(self.comparator) + ':{col_name}', fontsize=5)
-        if show:
-          plt.show()
-        if save_path:
-          g.savefig(save_path)
-
-    return all_dfs if isinstance(all_dfs, pd.DataFrame) else None
-
-  def all(
-      self,
-      output_folder: str,
-      confidence_threshold: float = 0.5,
-      iou_threshold: float = 0.5,
-      overwrite: bool = False,
-      metric_kwargs: dict = {},
-      pr_plot_kwargs: dict = {},
-      roc_plot_kwargs: dict = {},
-  ):
-    """Run all comparison methods one by one:
-    - detailed_summary
-    - pr_curve (if applicable)
-    - pr_plot
-    - confusion_matrix (if applicable)
-    And save to output_folder
-
-    Args:
-      output_folder (str): path to output
-      confidence_threshold (float): confidence threshold, applicable for classification and detection. Default is 0.5.
-      iou_threshold (float): iou threshold, support in range(0.5, 1., step=0.1) applicable for detection.
-      overwrite (bool): overwrite result of output_folder.
-      metric_kwargs (dict): keyword args for `eval_handler[...].model.{method}`, except for {confidence_threshold, iou_threshold}.
-      roc_plot_kwargs (dict): for relplot_kwargs of `roc_curve_plot` method.
-      pr_plot_kwargs (dict): for relplot_kwargs of `pr_plot` method.
-    """
-    eval_type = get_eval_type(self.model_type)
-    area = metric_kwargs.pop("area", "all")
-    bypass_const = metric_kwargs.pop("bypass_const", False)
-
-    fname = f"conf-{confidence_threshold}"
-    if eval_type == EvalType.DETECTION:
-      fname = f"{fname}_iou-{iou_threshold}_area-{area}"
-
-    def join_root(*args):
-      return os.path.join(output_folder, *args)
-
-    output_folder = join_root(fname)
-    if os.path.exists(output_folder) and not overwrite:
-      raise RuntimeError(f"{output_folder} exists. If you want to overwrite, set `overwrite=True`")
-
-    os.makedirs(output_folder, exist_ok=True)
-
-    logger.info("Making summary tables...")
-    dfs = self.detailed_summary(
-        confidence_threshold=confidence_threshold,
-        iou_threshold=iou_threshold,
-        area=area,
-        bypass_const=bypass_const)
-    if dfs is not None:
-      concept_df, total_df = dfs
-      concept_df.to_csv(join_root("concepts_summary.csv"))
-      total_df.to_csv(join_root("total_summary.csv"))
-
-    curve_metric_kwargs = dict(
-        confidence_threshold=confidence_threshold, iou_threshold=iou_threshold)
-    curve_metric_kwargs.update(metric_kwargs)
-
-    self.roc_curve_plot(
-        show=False,
-        save_path=join_root("roc.jpg"),
-        roc_curve_kwargs=curve_metric_kwargs,
-        relplot_kwargs=roc_plot_kwargs)
-
-    self.pr_plot(
-        show=False,
-        save_path=join_root("pr.jpg"),
-        pr_curve_kwargs=curve_metric_kwargs,
-        relplot_kwargs=pr_plot_kwargs)
-
-    self.confusion_matrix(
-        show=False, save_path=join_root("confusion_matrix.jpg"), cm_kwargs=curve_metric_kwargs)
-
-    logger.info(f"Done. Your outputs are saved at {output_folder}")
+__all__ = ["EvalResultCompare"]