ecopipeline 0.6.9__tar.gz → 0.7.0__tar.gz

{ecopipeline-0.6.9/src/ecopipeline.egg-info → ecopipeline-0.7.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ecopipeline
-Version: 0.6.9
+Version: 0.7.0
 Summary: Contains functions for use in Ecotope Datapipelines
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: GNU General Public License (GPL)

{ecopipeline-0.6.9 → ecopipeline-0.7.0}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = ecopipeline
-version = 0.6.9
+version = 0.7.0
 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-0.7.0/src/ecopipeline/load/__init__.py

@@ -0,0 +1,3 @@
+from .load import check_table_exists, create_new_table, load_overwrite_database, load_event_table, report_data_loss, load_data_statistics
+__all__ = ["check_table_exists", "create_new_table", "load_overwrite_database", "load_event_table", "report_data_loss",
+           "load_data_statistics"]

{ecopipeline-0.6.9 → ecopipeline-0.7.0}/src/ecopipeline/load/load.py

@@ -460,6 +460,27 @@ def report_data_loss(config : ConfigManager, site_name : str = None):
     cursor.close()
     return True
 
+def load_data_statistics(config : ConfigManager, daily_stats_df : pd.DataFrame, config_daily_indicator : str = "day"):
+    """
+    Logs data statistics for the site in a table with name "{daily table name}_stats"
+
+    Parameters
+    ----------  
+    config : ecopipeline.ConfigManager
+        The ConfigManager object that holds configuration data for the pipeline.
+    daily_stats_df : pd.DataFrame
+        dataframe created by the create_data_statistics_df() function in ecopipeline.transform
+    config_daily_indicator : str
+        the indicator of the daily_table name in the config.ini file of the data pipeline
+
+    Returns
+    ------- 
+    bool: 
+        A boolean value indicating if the data was successfully written to the database. 
+    """
+    table_name = f"{config.get_table_name(config_daily_indicator)}_stats"
+    return load_overwrite_database(config, daily_stats_df, config.get_db_table_info([]), config_daily_indicator, table_name=table_name)
+
 def _generate_mysql_update_event_table(row, id):
     statement = f"UPDATE site_events SET "
     statment_elems = []

{ecopipeline-0.6.9 → ecopipeline-0.7.0}/src/ecopipeline/transform/__init__.py

@@ -1,9 +1,16 @@
-from .transform import rename_sensors, avg_duplicate_times, remove_outliers, ffill_missing, nullify_erroneous, sensor_adjustment, round_time, aggregate_df, join_to_hourly, concat_last_row, join_to_daily, cop_method_1, cop_method_2, create_summary_tables, remove_partial_days,convert_c_to_f,convert_l_to_g, convert_on_off_col_to_bool, flag_dhw_outage,generate_event_log_df,convert_time_zone, shift_accumulative_columns,heat_output_calc, add_relative_humidity, apply_equipment_cop_derate
-from .lbnl import nclarity_filter_new, site_specific, condensate_calculations, gas_valve_diff, gather_outdoor_conditions, aqsuite_prep_time, nclarity_csv_to_df, _add_date, add_local_time, aqsuite_filter_new, get_refrig_charge, elev_correction, change_ID_to_HVAC, get_hvac_state, get_cop_values, get_cfm_values, replace_humidity, create_fan_curves, lbnl_temperature_conversions, lbnl_pressure_conversions, lbnl_sat_calculations, get_site_cfm_info, get_site_info, merge_indexlike_rows
+from .transform import rename_sensors, avg_duplicate_times, remove_outliers, ffill_missing, nullify_erroneous, sensor_adjustment, round_time, \
+    aggregate_df, join_to_hourly, concat_last_row, join_to_daily, cop_method_1, cop_method_2, create_summary_tables, remove_partial_days, \
+    convert_c_to_f,convert_l_to_g, convert_on_off_col_to_bool, flag_dhw_outage,generate_event_log_df,convert_time_zone, shift_accumulative_columns, \
+    heat_output_calc, add_relative_humidity, apply_equipment_cop_derate, create_data_statistics_df, delete_erroneous_from_time_pt
+from .lbnl import nclarity_filter_new, site_specific, condensate_calculations, gas_valve_diff, gather_outdoor_conditions, aqsuite_prep_time, \
+    nclarity_csv_to_df, _add_date, add_local_time, aqsuite_filter_new, get_refrig_charge, elev_correction, change_ID_to_HVAC, get_hvac_state, \
+    get_cop_values, get_cfm_values, replace_humidity, create_fan_curves, lbnl_temperature_conversions, lbnl_pressure_conversions, \
+    lbnl_sat_calculations, get_site_cfm_info, get_site_info, merge_indexlike_rows
 from .bayview import calculate_cop_values, aggregate_values, get_energy_by_min, verify_power_energy, get_temp_zones120, get_storage_gals120
 __all__ = ["rename_sensors", "avg_duplicate_times", "remove_outliers", "ffill_missing", "nullify_erroneous", "sensor_adjustment", "round_time", "aggregate_df", "join_to_hourly", "concat_last_row", "join_to_daily", 
            "cop_method_1", "cop_method_2", "create_summary_tables", "remove_partial_days", "nclarity_filter_new", "site_specific", "condensate_calculations", "gas_valve_diff", "gather_outdoor_conditions", "aqsuite_prep_time", 
            "nclarity_csv_to_df", "_add_date", "add_local_time", "aqsuite_filter_new", "get_refrig_charge", "elev_correction", "change_ID_to_HVAC", "get_hvac_state", "get_cop_values", "get_cfm_values", "replace_humidity", 
            "create_fan_curves", "lbnl_temperature_conversions", "lbnl_pressure_conversions", "lbnl_sat_calculations", "get_site_cfm_info", "get_site_info", "merge_indexlike_rows", "calculate_cop_values", "aggregate_values", 
            "get_energy_by_min", "verify_power_energy", "get_temp_zones120", "get_storage_gals120","convert_c_to_f","convert_l_to_g", "convert_on_off_col_to_bool", "flag_dhw_outage","generate_event_log_df","convert_time_zone",
-           "shift_accumulative_columns","heat_output_calc", "add_relative_humidity","apply_equipment_cop_derate"]
+           "shift_accumulative_columns","heat_output_calc", "add_relative_humidity","apply_equipment_cop_derate","create_data_statistics_df",
+           "delete_erroneous_from_time_pt"]

{ecopipeline-0.6.9 → ecopipeline-0.7.0}/src/ecopipeline/transform/transform.py

@@ -306,6 +306,35 @@ def ffill_missing(original_df: pd.DataFrame, config : ConfigManager, previous_fi
     df.apply(_ffill, args=(ffill_df,previous_fill))
     return df
 
+def delete_erroneous_from_time_pt(df: pd.DataFrame, time_point : pd.Timestamp, column_names : list, new_value = None) -> pd.DataFrame:
+    """
+    Function will take a pandas dataframe and delete specified erroneous values at a specified time point. 
+
+    Parameters
+    ---------- 
+    df: pd.DataFrame
+        Timestamp indexed Pandas dataframe that needs to have an erroneous value removed
+    time_point : pd.Timestamp
+        The timepoint index the erroneous value takes place in  
+    column_names : list
+        list of column names as strings that contain erroneous values at this time stamp
+    new_value : any
+        new value to populate the erroneous columns at this timestamp with. If set to None, will replace value with NaN
+    
+    Returns
+    ------- 
+    pd.DataFrame: 
+        Pandas dataframe with error values replaced with new value
+    """
+    if new_value is None:
+        new_value = float('NaN')  # Replace with NaN if new_value is not provided
+    
+    if time_point in df.index:
+        for col in column_names:
+            df.loc[time_point, col] = new_value
+
+    return df
+
 # TODO test this
 def nullify_erroneous(original_df: pd.DataFrame, config : ConfigManager) -> pd.DataFrame:
     """
@@ -998,7 +1027,7 @@ def join_to_daily(daily_data: pd.DataFrame, cop_data: pd.DataFrame) -> pd.DataFr
     out_df = daily_data.join(cop_data)
     return out_df
 
-def apply_equipment_cop_derate(df: pd.DataFrame, equip_cop_col: str, r_val : int = 16):
+def apply_equipment_cop_derate(df: pd.DataFrame, equip_cop_col: str, r_val : int = 16) -> pd.DataFrame:
     """
     Function derates equipment COP based on R value
     R12 - R16 : 12 %
@@ -1041,3 +1070,70 @@ def apply_equipment_cop_derate(df: pd.DataFrame, equip_cop_col: str, r_val : int
     
     df[equip_cop_col] =  df[equip_cop_col] * derate
     return df
+
+def create_data_statistics_df(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Function must be called on the raw minute data df after the rename_varriables() and before the ffill_missing() function has been called.
+    The function returns a dataframe indexed by day. Each column will expanded to 3 columns, appended with '_missing_mins', '_avg_gap', and
+    '_max_gap' respectively. the columns will carry the following statisctics:
+    _missing_mins -> the number of minutes in the day that have no reported data value for the column
+    _avg_gap -> the average gap (in minutes) between collected data values that day
+    _max_gap -> the maximum gap (in minutes) between collected data values that day
+
+    Parameters
+    ---------- 
+    df : pd.DataFrame
+        minute data df after the rename_varriables() and before the ffill_missing() function has been called
+
+    Returns
+    -------
+    daily_data_stats : pd.DataFrame
+        new dataframe with the columns descriped in the function's description
+    """
+    min_time = df.index.min()
+    start_day = min_time.floor('D')
+
+    # If min_time is not exactly at the start of the day, move to the next day
+    if min_time != start_day:
+        start_day = start_day + pd.tseries.offsets.Day(1)
+
+    # Build a complete minutely timestamp index over the full date range
+    full_index = pd.date_range(start=start_day,
+                               end=df.index.max().floor('D') - pd.Timedelta(minutes=1),
+                               freq='T')
+    
+    # Reindex to include any completely missing minutes
+    df_full = df.reindex(full_index)
+
+    # 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
+
+    # Function to calculate average consecutive missing values
+    def avg_consecutive_nans(x):
+        is_na = x.isna()
+        groups = (is_na != is_na.shift()).cumsum()
+        gap_lengths = is_na.groupby(groups).sum()
+        gap_lengths = gap_lengths[gap_lengths > 0]
+        if len(gap_lengths) == 0:
+            return 0
+        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))
+
+    # Rename columns to include a suffix
+    total_missing = total_missing.add_suffix('_missing_mins')
+    max_consec_missing = max_consec_missing.add_suffix('_max_gap')
+    avg_consec_missing = avg_consec_missing.add_suffix('_avg_gap')
+
+    # Concatenate along columns (axis=1)
+    combined_df = pd.concat([total_missing, max_consec_missing, avg_consec_missing], axis=1)
+
+    return combined_df

{ecopipeline-0.6.9 → ecopipeline-0.7.0}/src/ecopipeline/utils/ConfigManager.py

@@ -134,15 +134,22 @@ class ConfigManager:
             tables. 
         """
 
-        configure = configparser.ConfigParser()
-        configure.read(self.config_directory)
-
-        db_table_info = {header: {"table_name": configure.get(header, 'table_name')} for header in table_headers}
+        db_table_info = {}
+        if len(table_headers) > 0:
+            configure = configparser.ConfigParser()
+            configure.read(self.config_directory)
+            db_table_info = {header: {"table_name": configure.get(header, 'table_name')} for header in table_headers}
         db_table_info["database"] = self.db_connection_info["database"]
 
         print(f"Successfully fetched configuration information from file path {self.config_directory}.")
         return db_table_info
     
+    def get_table_name(self, header):
+        configure = configparser.ConfigParser()
+        configure.read(self.config_directory)
+
+        return configure.get(header, 'table_name')
+    
     def get_db_name(self):
         """
         returns name of database that data will be uploaded to

{ecopipeline-0.6.9 → ecopipeline-0.7.0/src/ecopipeline.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ecopipeline
-Version: 0.6.9
+Version: 0.7.0
 Summary: Contains functions for use in Ecotope Datapipelines
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: GNU General Public License (GPL)

ecopipeline-0.6.9/src/ecopipeline/load/__init__.py

@@ -1,2 +0,0 @@
-from .load import check_table_exists, create_new_table, load_overwrite_database, load_event_table, report_data_loss
-__all__ = ["check_table_exists", "create_new_table", "load_overwrite_database", "load_event_table", "report_data_loss"]