ecopipeline 0.8.6__tar.gz → 0.8.8__tar.gz

{ecopipeline-0.8.6/src/ecopipeline.egg-info → ecopipeline-0.8.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ecopipeline
-Version: 0.8.6
+Version: 0.8.8
 Summary: Contains functions for use in Ecotope Datapipelines
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: GNU General Public License (GPL)

{ecopipeline-0.8.6 → ecopipeline-0.8.8}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = ecopipeline
-version = 0.8.6
+version = 0.8.8
 authors = ["Carlos Bello, <bellocarlos@seattleu.edu>, Emil Fahrig <fahrigemil@seattleu.edu>, Casey Mang <cmang@seattleu.edu>, Julian Harris <harrisjulian@seattleu.edu>, Roger Tram <rtram@seattleu.edu>, Nolan Price <nolan@ecotope.com>"]
 description = Contains functions for use in Ecotope Datapipelines
 long_description = file: README.md

{ecopipeline-0.8.6 → ecopipeline-0.8.8}/src/ecopipeline/extract/extract.py

@@ -658,7 +658,7 @@ def egauge_csv_to_df(csv_filenames: List[str]) -> pd.DataFrame:
 
     return df_diff
 
-def fm_api_to_df(config: ConfigManager, startTime: datetime = None, endTime: datetime = None) -> pd.DataFrame:
+def fm_api_to_df(config: ConfigManager, startTime: datetime = None, endTime: datetime = None, create_csv : bool = True) -> pd.DataFrame:
     """
     Function connects to the field manager api to pull data and returns a dataframe.
 
@@ -674,6 +674,8 @@ def fm_api_to_df(config: ConfigManager, startTime: datetime = None, endTime: dat
     endTime: datetime
         The point in time for which we want to end the data extraction. This 
         is local time from the data's index. 
+    create_csv : bool
+        create csv files as you process such that API need not be relied upon for reprocessing
     
     Returns
     ------- 
@@ -715,6 +717,12 @@ def fm_api_to_df(config: ConfigManager, startTime: datetime = None, endTime: dat
                 df.set_index('time_pt', inplace=True)
                 df = df.sort_index()
                 df = df.groupby(df.index).mean()
+            if create_csv:
+                filename = f"{startTime.strftime('%Y%m%d%H%M%S')}.csv"
+                original_directory = os.getcwd()
+                os.chdir(config.data_directory)
+                df.to_csv(filename, index_label='time_pt')
+                os.chdir(original_directory)
             return df
         elif response.status_code == 500:
             json_message = response.json()
@@ -753,7 +761,30 @@ def pull_egauge_data(config: ConfigManager, eGauge_ids: list, eGauge_usr : str,
 
     os.chdir(original_directory)
 
-def tb_api_to_df(config: ConfigManager, startTime: datetime = None, endTime: datetime = None):
+def tb_api_to_df(config: ConfigManager, startTime: datetime = None, endTime: datetime = None, create_csv : bool = True):
+    """
+    Function connects to the things board manager api to pull data and returns a dataframe.
+
+    Parameters
+    ----------  
+    config : ecopipeline.ConfigManager
+        The ConfigManager object that holds configuration data for the pipeline. The config manager
+        must contain information to connect to the api, i.e. the api user name and password as well as
+        the device id for the device the data is being pulled from.
+    startTime: datetime
+        The point in time for which we want to start the data extraction from. This 
+        is local time from the data's index. 
+    endTime: datetime
+        The point in time for which we want to end the data extraction. This 
+        is local time from the data's index. 
+    create_csv : bool
+        create csv files as you process such that API need not be relied upon for reprocessing
+    
+    Returns
+    ------- 
+    pd.DataFrame: 
+        Pandas Dataframe containing data from the API pull with column headers the same as the variable names in the data from the pull
+    """
     if endTime is None:
         endTime = datetime.now()
     if startTime is None:
@@ -770,7 +801,6 @@ def tb_api_to_df(config: ConfigManager, startTime: datetime = None, endTime: dat
         df = df.sort_index()
         df = df.groupby(df.index).mean()
         return df
-
     url = f'https://thingsboard.cloud/api/plugins/telemetry/DEVICE/{config.api_device_id}/values/timeseries'
     token = config.get_thingsboard_token()
     keys = _get_tb_keys(config, token)
@@ -808,8 +838,14 @@ def tb_api_to_df(config: ConfigManager, startTime: datetime = None, endTime: dat
             df = pd.DataFrame(data)
             df.index = pd.to_datetime(df.index, unit='ms')
             df = df.sort_index()
+            # save to file
+            if create_csv:
+                filename = f"{startTime.strftime('%Y%m%d%H%M%S')}.csv"
+                original_directory = os.getcwd()
+                os.chdir(config.data_directory)
+                df.to_csv(filename, index_label='time_pt')
+                os.chdir(original_directory)
             return df
-            
         print(f"Failed to make GET request. Status code: {response.status_code} {response.json()}")
         return pd.DataFrame()
     except Exception as e:

{ecopipeline-0.8.6 → ecopipeline-0.8.8}/src/ecopipeline/transform/transform.py

@@ -1104,19 +1104,23 @@ def create_data_statistics_df(df: pd.DataFrame) -> pd.DataFrame:
     
     # Reindex to include any completely missing minutes
     df_full = df.reindex(full_index)
-
+    # df_full = df_full.select_dtypes(include='number')
+    # print("1",df_full)
     # Resample daily to count missing values per column
     total_missing = df_full.isna().resample('D').sum().astype(int)
-
     # Function to calculate max consecutive missing values
     def max_consecutive_nans(x):
-        is_na = x.isna()
-        groups = (is_na != is_na.shift()).cumsum()
-        return is_na.groupby(groups).sum().max() or 0
+        try:
+            # print(f"here is x :{x}")
+            is_na = pd.Series(x).isna().reset_index(drop=True)
+            groups = (is_na != is_na.shift()).cumsum()
+            return is_na.groupby(groups).sum().max() or 0
+        except:
+            raise Exception(f"{x} is the problem!")
 
     # Function to calculate average consecutive missing values
     def avg_consecutive_nans(x):
-        is_na = x.isna()
+        is_na = pd.Series(x).isna().reset_index(drop=True)
         groups = (is_na != is_na.shift()).cumsum()
         gap_lengths = is_na.groupby(groups).sum()
         gap_lengths = gap_lengths[gap_lengths > 0]
@@ -1125,8 +1129,9 @@ def create_data_statistics_df(df: pd.DataFrame) -> pd.DataFrame:
         return gap_lengths.mean()
 
     # Apply daily, per column
-    max_consec_missing = df_full.resample('D').apply(lambda day: day.apply(max_consecutive_nans))
-    avg_consec_missing = df_full.resample('D').apply(lambda day: day.apply(avg_consecutive_nans))
+    # print("hello?",type(df_full.index))
+    max_consec_missing = df_full.resample('D').agg(max_consecutive_nans)
+    avg_consec_missing = df_full.resample('D').agg(avg_consecutive_nans)
 
     # Rename columns to include a suffix
     total_missing = total_missing.add_suffix('_missing_mins')

{ecopipeline-0.8.6 → ecopipeline-0.8.8/src/ecopipeline.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ecopipeline
-Version: 0.8.6
+Version: 0.8.8
 Summary: Contains functions for use in Ecotope Datapipelines
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: GNU General Public License (GPL)