def generate_appliances_traces(schema,
table,
appliances,
dataid,
sample_rate=None,
verbose=True):
'''
Return a list of appliance traces by dataid. Each trace is in decimal form
and in average Watts.
'''
global schema_names, source
schema_name = schema_names[schema]
query = 'select {0},{1} from "{2}".{3} where dataid={4}'.format(
','.join(appliances), time_columns[schema], schema_name, table, dataid)
if verbose:
print query
df = get_dataframe(query)
df = df.rename(columns={time_columns[schema]: 'time'})
utils.create_datetimeindex(df)
traces = []
for appliance in appliances:
series = pd.Series(df[appliance], name=appliance).fillna(0)
metadata = {
'source': source,
'schema': schema,
'table': table,
'dataid': dataid,
'device_name': series.name,
}
trace = ApplianceTrace(series, metadata)
if sample_rate:
trace = trace.resample(sample_rate)
traces.append(trace)
return traces
def generate_appliances_traces(
schema,table,appliances,dataid,sample_rate=None,verbose=True):
'''
Return a list of appliance traces by dataid. Each trace is in decimal form
and in average Watts.
'''
global schema_names, source
schema_name = schema_names[schema]
query= 'select {0},{1} from "{2}".{3} where dataid={4}'.format(
','.join(appliances), time_columns[schema], schema_name, table, dataid)
if verbose:
print query
df = get_dataframe(query)
df = df.rename(columns={time_columns[schema]: 'time'})
utils.create_datetimeindex(df)
traces = []
for appliance in appliances:
series = pd.Series(df[appliance],name = appliance).fillna(0)
metadata = {'source':source,
'schema':schema,
'table':table ,
'dataid':dataid,
'device_name':series.name,
}
trace = ApplianceTrace(series,metadata)
if sample_rate:
trace = trace.resample(sample_rate)
traces.append(trace)
return traces
def clean_dataframe(df, schema, drop_cols):
'''
Cleans a dataframe queried directly from the database by renaming the db
time column (ex. UTC_15MIN) to a column name 'time'. It then converts the
time column to datetime objects and reindexes the dataframe to the time
column before dropping that column from the dataframe. It also drops any
columns included in the list drop_cols. The columns 'id' and 'dataid' are
also dropped.
'''
# change the time column name
global time_columns
df = df.rename(columns={time_columns[schema]: 'time'})
# use a DatetimeIndex
utils.create_datetimeindex(df)
# drop unnecessary columns
df = df.drop(['dataid'], axis=1)
if schema == 'curated':
df = df.drop(['id'], axis=1)
if len(drop_cols) != 0:
df = df.drop(drop_cols, axis=1)
return df
def clean_dataframe(df,schema,drop_cols):
'''
Cleans a dataframe queried directly from the database by renaming the db
time column (ex. UTC_15MIN) to a column name 'time'. It then converts the
time column to datetime objects and reindexes the dataframe to the time
column before dropping that column from the dataframe. It also drops any
columns included in the list drop_cols. The columns 'id' and 'dataid' are
also dropped.
'''
# change the time column name
global time_columns
df = df.rename(columns={time_columns[schema]: 'time'})
# use a DatetimeIndex
utils.create_datetimeindex(df)
# drop unnecessary columns
df = df.drop(['dataid'], axis=1)
if schema == 'curated':
df = df.drop(['id'], axis=1)
if len(drop_cols)!=0:
df= df.drop(drop_cols,axis=1)
return df
