rasmus/nafuma
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Standardise data flow

Browse source
This commit is contained in:
rasmusvt 2022-04-22 15:19:36 +02:00
parent 95e411ac21
commit 514a20604b
2 changed files with 169 additions and 214 deletions
Download patch file Download diff file Expand all files Collapse all files

276
nafuma/electrochemistry/io.py
View file

@ -1,40 +1,28 @@
from email.policy import default
import pandas as pd import pandas as pd
import numpy as np import numpy as np
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
import os import os
import nafuma.auxillary as aux
from sympy import re
def read_data(path, kind, options=None): def read_data(data, options=None):
if kind == 'neware': if data['kind'] == 'neware':
df = read_neware(path) df = read_neware(data['path'])
cycles = process_neware_data(df, options=options) cycles = process_neware_data(df=df, options=options)
elif kind == 'batsmall': elif data['kind'] == 'batsmall':
df = read_batsmall(path) df = read_batsmall(data['path'])
cycles = process_batsmall_data(df=df, options=options) cycles = process_batsmall_data(df=df, options=options)
elif kind == 'biologic': elif data['kind'] == 'biologic':
df = read_biologic(path) df = read_biologic(data['path'])
cycles = process_biologic_data(df=df, options=options) cycles = process_biologic_data(df=df, options=options)
return cycles return cycles
def read_batsmall(path):
''' Reads BATSMALL-data into a DataFrame.
Input:
path (required): string with path to datafile
Output:
df: pandas DataFrame containing the data as-is, but without additional NaN-columns.'''
df = pd.read_csv(path, skiprows=2, sep='\t')
df = df.loc[:, ~df.columns.str.contains('^Unnamed')]
return df
def read_neware(path, summary=False): def read_neware(path, summary=False):
@ -43,6 +31,8 @@ def read_neware(path, summary=False):
type is .csv, it will just open the datafile and it does not matter if summary is False or not.''' type is .csv, it will just open the datafile and it does not matter if summary is False or not.'''
from xlsx2csv import Xlsx2csv from xlsx2csv import Xlsx2csv
# FIXME Do a check if a .csv-file already exists even if the .xlsx is passed
# Convert from .xlsx to .csv to make readtime faster # Convert from .xlsx to .csv to make readtime faster
if path.split('.')[-1] == 'xlsx': if path.split('.')[-1] == 'xlsx':
csv_details = ''.join(path.split('.')[:-1]) + '_details.csv' csv_details = ''.join(path.split('.')[:-1]) + '_details.csv'
@ -66,6 +56,20 @@ def read_neware(path, summary=False):
return df return df
def read_batsmall(path):
''' Reads BATSMALL-data into a DataFrame.
Input:
path (required): string with path to datafile
Output:
df: pandas DataFrame containing the data as-is, but without additional NaN-columns.'''
df = pd.read_csv(path, skiprows=2, sep='\t')
df = df.loc[:, ~df.columns.str.contains('^Unnamed')]
return df
def read_biologic(path): def read_biologic(path):
''' Reads Bio-Logic-data into a DataFrame. ''' Reads Bio-Logic-data into a DataFrame.
@ -89,10 +93,6 @@ def read_biologic(path):
def process_batsmall_data(df, options=None): def process_batsmall_data(df, options=None):
''' Takes BATSMALL-data in the form of a DataFrame and cleans the data up and converts units into desired units. ''' Takes BATSMALL-data in the form of a DataFrame and cleans the data up and converts units into desired units.
Splits up into individual charge and discharge DataFrames per cycle, and outputs a list where each element is a tuple with the Chg and DChg-data. E.g. cycles[10][0] gives the charge data for the 11th cycle. Splits up into individual charge and discharge DataFrames per cycle, and outputs a list where each element is a tuple with the Chg and DChg-data. E.g. cycles[10][0] gives the charge data for the 11th cycle.
@ -111,26 +111,25 @@ def process_batsmall_data(df, options=None):
''' '''
required_options = ['splice_cycles', 'molecular_weight', 'reverse_discharge', 'units'] required_options = ['splice_cycles', 'molecular_weight', 'reverse_discharge', 'units']
default_options = {'splice_cycles': False, 'molecular_weight': None, 'reverse_discharge': False, 'units': None}
default_options = {
'splice_cycles': False,
'molecular_weight': None,
'reverse_discharge': False,
'units': None}
if not options:
options = default_options
else:
for option in required_options:
if option not in options.keys():
options[option] = default_options[option]
aux.update_options(options=options, required_options=required_options, default_options=default_options)
options['kind'] = 'batsmall'
# Complete set of new units and get the units used in the dataset, and convert values in the DataFrame from old to new. # Complete set of new units and get the units used in the dataset, and convert values in the DataFrame from old to new.
new_units = set_units(units=options['units']) set_units(options)
old_units = get_old_units(df, kind='batsmall') options['old_units'] = get_old_units(df, options)
df = unit_conversion(df=df, new_units=new_units, old_units=old_units, kind='batsmall')
options['units'] = new_units
df = unit_conversion(df=df, options=options)
if options['splice_cycles']: if options['splice_cycles']:
df = splice_cycles(df=df, kind='batsmall') df = splice_cycles(df=df, options=options)
# Replace NaN with empty string in the Comment-column and then remove all steps where the program changes - this is due to inconsistent values for current # Replace NaN with empty string in the Comment-column and then remove all steps where the program changes - this is due to inconsistent values for current
df[["comment"]] = df[["comment"]].fillna(value={'comment': ''}) df[["comment"]] = df[["comment"]].fillna(value={'comment': ''})
@ -173,23 +172,21 @@ def process_batsmall_data(df, options=None):
cycles.append((chg_df, dchg_df)) cycles.append((chg_df, dchg_df))
return cycles return cycles
def splice_cycles(df, kind): def splice_cycles(df, options: dict) -> pd.DataFrame:
''' Splices two cycles together - if e.g. one charge cycle are split into several cycles due to change in parameters.
Incomplete, only accomodates BatSmall so far.'''
if kind == 'batsmall': if options['kind'] == 'batsmall':
# Creates masks for charge and discharge curves # Creates masks for charge and discharge curves
chg_mask = df['current'] >= 0 chg_mask = df['current'] >= 0
dchg_mask = df['current'] < 0 dchg_mask = df['current'] < 0
# Get the number of cycles in the dataset # Loop through all the cycling steps, change the current and capacities in the
max_count = df["count"].max()
# Loop through all the cycling steps, change the current and capacities in the
for i in range(df["count"].max()): for i in range(df["count"].max()):
sub_df = df.loc[df['count'] == i+1] sub_df = df.loc[df['count'] == i+1]
sub_df_chg = sub_df.loc[chg_mask] sub_df_chg = sub_df.loc[chg_mask]
@ -233,7 +230,7 @@ def splice_cycles(df, kind):
def process_neware_data(df, options=None): def process_neware_data(df, options={}):
""" Takes data from NEWARE in a DataFrame as read by read_neware() and converts units, adds columns and splits into cycles. """ Takes data from NEWARE in a DataFrame as read by read_neware() and converts units, adds columns and splits into cycles.
@ -245,25 +242,26 @@ def process_neware_data(df, options=None):
molecular_weight: the molar mass (in g mol^-1) of the active material, to calculate the number of ions extracted. Assumes one electron per Li+/Na+-ion """ molecular_weight: the molar mass (in g mol^-1) of the active material, to calculate the number of ions extracted. Assumes one electron per Li+/Na+-ion """
required_options = ['units', 'active_material_weight', 'molecular_weight', 'reverse_discharge', 'splice_cycles'] required_options = ['units', 'active_material_weight', 'molecular_weight', 'reverse_discharge', 'splice_cycles']
default_options = {'units': None, 'active_material_weight': None, 'molecular_weight': None, 'reverse_discharge': False, 'splice_cycles': None}
default_options = {
'units': None,
'active_material_weight': None,
'molecular_weight': None,
'reverse_discharge': False,
'splice_cycles': None}
if not options:
options = default_options aux.update_options(options=options, required_options=required_options, default_options=default_options)
else: options['kind'] = 'neware'
for option in required_options:
if option not in options.keys():
options[option] = default_options[option]
# Complete set of new units and get the units used in the dataset, and convert values in the DataFrame from old to new. # Complete set of new units and get the units used in the dataset, and convert values in the DataFrame from old to new.
new_units = set_units(units=options['units']) set_units(options=options) # sets options['units']
old_units = get_old_units(df=df, kind='neware') options['old_units'] = get_old_units(df=df, options=options)
df = add_columns(df=df, active_material_weight=options['active_material_weight'], molecular_weight=options['molecular_weight'], old_units=old_units, kind='neware') df = add_columns(df=df, options=options) # adds columns to the DataFrame if active material weight and/or molecular weight has been passed in options
df = unit_conversion(df=df, new_units=new_units, old_units=old_units, kind='neware') df = unit_conversion(df=df, options=options) # converts all units from the old units to the desired units
options['units'] = new_units
# Creates masks for charge and discharge curves # Creates masks for charge and discharge curves
@ -288,6 +286,8 @@ def process_neware_data(df, options=None):
if chg_df.empty and dchg_df.empty: if chg_df.empty and dchg_df.empty:
continue continue
# Reverses the discharge curve if specified
if options['reverse_discharge']: if options['reverse_discharge']:
max_capacity = dchg_df['capacity'].max() max_capacity = dchg_df['capacity'].max()
dchg_df['capacity'] = np.abs(dchg_df['capacity'] - max_capacity) dchg_df['capacity'] = np.abs(dchg_df['capacity'] - max_capacity)
@ -310,35 +310,34 @@ def process_neware_data(df, options=None):
def process_biologic_data(df, options=None): def process_biologic_data(df, options=None):
required_options = ['units', 'active_material_weight', 'molecular_weight', 'reverse_discharge', 'splice_cycles'] required_options = ['units', 'active_material_weight', 'molecular_weight', 'reverse_discharge', 'splice_cycles']
default_options = {'units': None, 'active_material_weight': None, 'molecular_weight': None, 'reverse_discharge': False, 'splice_cycles': None}
default_options = {
'units': None,
'active_material_weight': None,
'molecular_weight': None,
'reverse_discharge': False,
'splice_cycles': None}
if not options:
options = default_options aux.update_options(options=options, required_options=required_options, default_options=default_options)
else: options['kind'] = 'biologic'
for option in required_options:
if option not in options.keys():
options[option] = default_options[option]
# Pick out necessary columns # Pick out necessary columns
df = df[['Ns changes', 'Ns', 'time/s', 'Ewe/V', 'Energy charge/W.h', 'Energy discharge/W.h', '<I>/mA', 'Capacity/mA.h', 'cycle number']].copy() df = df[['Ns changes', 'Ns', 'time/s', 'Ewe/V', 'Energy charge/W.h', 'Energy discharge/W.h', '<I>/mA', 'Capacity/mA.h', 'cycle number']].copy()
# Complete set of new units and get the units used in the dataset, and convert values in the DataFrame from old to new. # Complete set of new units and get the units used in the dataset, and convert values in the DataFrame from old to new.
new_units = set_units(units=options['units']) set_units(options)
old_units = get_old_units(df=df, kind='biologic') options['old_units'] = get_old_units(df=df, options=options)
df = add_columns(df=df, active_material_weight=options['active_material_weight'], molecular_weight=options['molecular_weight'], old_units=old_units, kind='biologic') df = add_columns(df=df, options=options)
df = unit_conversion(df=df, new_units=new_units, old_units=old_units, kind='biologic')
options['units'] = new_units
df = unit_conversion(df=df, options=options)
# Creates masks for charge and discharge curves # Creates masks for charge and discharge curves
chg_mask = (df['status'] == 1) & (df['status_change'] != 1) chg_mask = (df['status'] == 1) & (df['status_change'] != 1)
dchg_mask = (df['status'] == 2) & (df['status_change'] != 1) dchg_mask = (df['status'] == 2) & (df['status_change'] != 1)
# Initiate cycles list # Initiate cycles list
cycles = [] cycles = []
@ -376,62 +375,62 @@ def process_biologic_data(df, options=None):
return cycles return cycles
def add_columns(df, active_material_weight, molecular_weight, old_units, kind): def add_columns(df, options):
if kind == 'neware': if options['kind'] == 'neware':
if active_material_weight: if options['active_material_weight']:
df["SpecificCapacity({}/mg)".format(old_units["capacity"])] = df["Capacity({})".format(old_units['capacity'])] / (active_material_weight) df["SpecificCapacity({}/mg)".format(options['old_units']["capacity"])] = df["Capacity({})".format(options['old_units']['capacity'])] / (options['active_material_weight'])
if molecular_weight: if options['molecular_weight']:
faradays_constant = 96485.3365 # [F] = C mol^-1 = As mol^-1 faradays_constant = 96485.3365 # [F] = C mol^-1 = As mol^-1
seconds_per_hour = 3600 # s h^-1 seconds_per_hour = 3600 # s h^-1
f = faradays_constant / seconds_per_hour * 1000.0 # [f] = mAh mol^-1 f = faradays_constant / seconds_per_hour * 1000.0 # [f] = mAh mol^-1
df["IonsExtracted"] = (df["SpecificCapacity({}/mg)".format(old_units['capacity'])]*molecular_weight)*1000/f df["IonsExtracted"] = (df["SpecificCapacity({}/mg)".format(options['old_units']['capacity'])]*options['molecular_weight'])*1000/f
if kind == 'biologic': if options['kind'] == 'biologic':
if active_material_weight: if options['active_material_weight']:
capacity = old_units['capacity'].split('h')[0] + '.h' capacity = options['old_units']['capacity'].split('h')[0] + '.h'
df["SpecificCapacity({}/mg)".format(old_units["capacity"])] = df["Capacity/{}".format(capacity)] / (active_material_weight) df["SpecificCapacity({}/mg)".format(options['old_units']["capacity"])] = df["Capacity/{}".format(capacity)] / (options['active_material_weight'])
if molecular_weight: if options['molecular_weight']:
faradays_constant = 96485.3365 # [F] = C mol^-1 = As mol^-1 faradays_constant = 96485.3365 # [F] = C mol^-1 = As mol^-1
seconds_per_hour = 3600 # s h^-1 seconds_per_hour = 3600 # s h^-1
f = faradays_constant / seconds_per_hour * 1000.0 # [f] = mAh mol^-1 f = faradays_constant / seconds_per_hour * 1000.0 # [f] = mAh mol^-1
df["IonsExtracted"] = (df["SpecificCapacity({}/mg)".format(old_units['capacity'])]*molecular_weight)*1000/f df["IonsExtracted"] = (df["SpecificCapacity({}/mg)".format(options['old_units']['capacity'])]*options['molecular_weight'])*1000/f
return df return df
def unit_conversion(df, new_units, old_units, kind): def unit_conversion(df, options):
from . import unit_tables from . import unit_tables
if kind == 'batsmall': if options['kind'] == 'batsmall':
df["TT [{}]".format(old_units["time"])] = df["TT [{}]".format(old_units["time"])] * unit_tables.time()[old_units["time"]].loc[new_units['time']] df["TT [{}]".format(options['old_units']["time"])] = df["TT [{}]".format(options['old_units']["time"])] * unit_tables.time()[options['old_units']["time"]].loc[options['units']['time']]
df["U [{}]".format(old_units["voltage"])] = df["U [{}]".format(old_units["voltage"])] * unit_tables.voltage()[old_units["voltage"]].loc[new_units['voltage']] df["U [{}]".format(options['old_units']["voltage"])] = df["U [{}]".format(options['old_units']["voltage"])] * unit_tables.voltage()[options['old_units']["voltage"]].loc[options['units']['voltage']]
df["I [{}]".format(old_units["current"])] = df["I [{}]".format(old_units["current"])] * unit_tables.current()[old_units["current"]].loc[new_units['current']] df["I [{}]".format(options['old_units']["current"])] = df["I [{}]".format(options['old_units']["current"])] * unit_tables.current()[options['old_units']["current"]].loc[options['units']['current']]
df["C [{}/{}]".format(old_units["capacity"], old_units["mass"])] = df["C [{}/{}]".format(old_units["capacity"], old_units["mass"])] * (unit_tables.capacity()[old_units["capacity"]].loc[new_units["capacity"]] / unit_tables.mass()[old_units["mass"]].loc[new_units["mass"]]) df["C [{}/{}]".format(options['old_units']["capacity"], options['old_units']["mass"])] = df["C [{}/{}]".format(options['old_units']["capacity"], options['old_units']["mass"])] * (unit_tables.capacity()[options['old_units']["capacity"]].loc[options['units']["capacity"]] / unit_tables.mass()[options['old_units']["mass"]].loc[options['units']["mass"]])
df.columns = ['time', 'voltage', 'current', 'count', 'specific_capacity', 'comment'] df.columns = ['time', 'voltage', 'current', 'count', 'specific_capacity', 'comment']
if kind == 'neware': if options['kind'] == 'neware':
df['Current({})'.format(old_units['current'])] = df['Current({})'.format(old_units['current'])] * unit_tables.current()[old_units['current']].loc[new_units['current']] df['Current({})'.format(options['old_units']['current'])] = df['Current({})'.format(options['old_units']['current'])] * unit_tables.current()[options['old_units']['current']].loc[options['units']['current']]
df['Voltage({})'.format(old_units['voltage'])] = df['Voltage({})'.format(old_units['voltage'])] * unit_tables.voltage()[old_units['voltage']].loc[new_units['voltage']] df['Voltage({})'.format(options['old_units']['voltage'])] = df['Voltage({})'.format(options['old_units']['voltage'])] * unit_tables.voltage()[options['old_units']['voltage']].loc[options['units']['voltage']]
df['Capacity({})'.format(old_units['capacity'])] = df['Capacity({})'.format(old_units['capacity'])] * unit_tables.capacity()[old_units['capacity']].loc[new_units['capacity']] df['Capacity({})'.format(options['old_units']['capacity'])] = df['Capacity({})'.format(options['old_units']['capacity'])] * unit_tables.capacity()[options['old_units']['capacity']].loc[options['units']['capacity']]
df['Energy({})'.format(old_units['energy'])] = df['Energy({})'.format(old_units['energy'])] * unit_tables.energy()[old_units['energy']].loc[new_units['energy']] df['Energy({})'.format(options['old_units']['energy'])] = df['Energy({})'.format(options['old_units']['energy'])] * unit_tables.energy()[options['old_units']['energy']].loc[options['units']['energy']]
df['CycleTime({})'.format(new_units['time'])] = df.apply(lambda row : convert_time_string(row['Relative Time(h:min:s.ms)'], unit=new_units['time']), axis=1) df['CycleTime({})'.format(options['units']['time'])] = df.apply(lambda row : convert_time_string(row['Relative Time(h:min:s.ms)'], unit=options['units']['time']), axis=1)
df['RunTime({})'.format(new_units['time'])] = df.apply(lambda row : convert_datetime_string(row['Real Time(h:min:s.ms)'], reference=df['Real Time(h:min:s.ms)'].iloc[0], unit=new_units['time']), axis=1) df['RunTime({})'.format(options['units']['time'])] = df.apply(lambda row : convert_datetime_string(row['Real Time(h:min:s.ms)'], reference=df['Real Time(h:min:s.ms)'].iloc[0], unit=options['units']['time']), axis=1)
columns = ['status', 'jump', 'cycle', 'steps', 'current', 'voltage', 'capacity', 'energy'] columns = ['status', 'jump', 'cycle', 'steps', 'current', 'voltage', 'capacity', 'energy']
if 'SpecificCapacity({}/mg)'.format(old_units['capacity']) in df.columns: if 'SpecificCapacity({}/mg)'.format(options['old_units']['capacity']) in df.columns:
df['SpecificCapacity({}/mg)'.format(old_units['capacity'])] = df['SpecificCapacity({}/mg)'.format(old_units['capacity'])] * unit_tables.capacity()[old_units['capacity']].loc[new_units['capacity']] / unit_tables.mass()['mg'].loc[new_units["mass"]] df['SpecificCapacity({}/mg)'.format(options['old_units']['capacity'])] = df['SpecificCapacity({}/mg)'.format(options['old_units']['capacity'])] * unit_tables.capacity()[options['old_units']['capacity']].loc[options['units']['capacity']] / unit_tables.mass()['mg'].loc[options['units']["mass"]]
columns.append('specific_capacity') columns.append('specific_capacity')
if 'IonsExtracted' in df.columns: if 'IonsExtracted' in df.columns:
@ -447,18 +446,18 @@ def unit_conversion(df, new_units, old_units, kind):
df.columns = columns df.columns = columns
if kind == 'biologic': if options['kind'] == 'biologic':
df['time/{}'.format(old_units['time'])] = df["time/{}".format(old_units["time"])] * unit_tables.time()[old_units["time"]].loc[new_units['time']] df['time/{}'.format(options['old_units']['time'])] = df["time/{}".format(options['old_units']["time"])] * unit_tables.time()[options['old_units']["time"]].loc[options['units']['time']]
df["Ewe/{}".format(old_units["voltage"])] = df["Ewe/{}".format(old_units["voltage"])] * unit_tables.voltage()[old_units["voltage"]].loc[new_units['voltage']] df["Ewe/{}".format(options['old_units']["voltage"])] = df["Ewe/{}".format(options['old_units']["voltage"])] * unit_tables.voltage()[options['old_units']["voltage"]].loc[options['units']['voltage']]
df["<I>/{}".format(old_units["current"])] = df["<I>/{}".format(old_units["current"])] * unit_tables.current()[old_units["current"]].loc[new_units['current']] df["<I>/{}".format(options['old_units']["current"])] = df["<I>/{}".format(options['old_units']["current"])] * unit_tables.current()[options['old_units']["current"]].loc[options['units']['current']]
capacity = old_units['capacity'].split('h')[0] + '.h' capacity = options['old_units']['capacity'].split('h')[0] + '.h'
df["Capacity/{}".format(capacity)] = df["Capacity/{}".format(capacity)] * (unit_tables.capacity()[old_units["capacity"]].loc[new_units["capacity"]]) df["Capacity/{}".format(capacity)] = df["Capacity/{}".format(capacity)] * (unit_tables.capacity()[options['old_units']["capacity"]].loc[options['units']["capacity"]])
columns = ['status_change', 'status', 'time', 'voltage', 'energy_charge', 'energy_discharge', 'current', 'capacity', 'cycle'] columns = ['status_change', 'status', 'time', 'voltage', 'energy_charge', 'energy_discharge', 'current', 'capacity', 'cycle']
if 'SpecificCapacity({}/mg)'.format(old_units['capacity']) in df.columns: if 'SpecificCapacity({}/mg)'.format(options['old_units']['capacity']) in df.columns:
df['SpecificCapacity({}/mg)'.format(old_units['capacity'])] = df['SpecificCapacity({}/mg)'.format(old_units['capacity'])] * unit_tables.capacity()[old_units['capacity']].loc[new_units['capacity']] / unit_tables.mass()['mg'].loc[new_units["mass"]] df['SpecificCapacity({}/mg)'.format(options['old_units']['capacity'])] = df['SpecificCapacity({}/mg)'.format(options['old_units']['capacity'])] * unit_tables.capacity()[options['old_units']['capacity']].loc[options['units']['capacity']] / unit_tables.mass()['mg'].loc[options['units']["mass"]]
columns.append('specific_capacity') columns.append('specific_capacity')
if 'IonsExtracted' in df.columns: if 'IonsExtracted' in df.columns:
@ -469,38 +468,43 @@ def unit_conversion(df, new_units, old_units, kind):
return df return df
def set_units(units=None): def set_units(options: dict) -> None:
# Complete the list of units - if not all are passed, then default value will be used # Complete the list of units - if not all are passed, then default value will be used
required_units = ['time', 'current', 'voltage', 'capacity', 'mass', 'energy', 'specific_capacity'] required_units = ['time', 'current', 'voltage', 'capacity', 'mass', 'energy', 'specific_capacity']
default_units = {'time': 'h', 'current': 'mA', 'voltage': 'V', 'capacity': 'mAh', 'mass': 'g', 'energy': 'mWh', 'specific_capacity': None}
if not units:
units = default_units
if units:
for unit in required_units:
if unit not in units.keys():
units[unit] = default_units[unit]
units['specific_capacity'] = r'{} {}'.format(units['capacity'], units['mass']) + '$^{-1}$'
return units
def get_old_units(df, kind):
if kind=='batsmall': default_units = {
'time': 'h',
'current': 'mA',
'voltage': 'V',
'capacity': 'mAh',
'mass': 'g',
'energy': 'mWh',
'specific_capacity': None}
if not options['units']:
options['units'] = default_units
aux.update_options(options=options['units'], required_options=required_units, default_options=default_units)
options['units']['specific_capacity'] = r'{} {}'.format(options['units']['capacity'], options['units']['mass']) + '$^{-1}$'
def get_old_units(df: pd.DataFrame, options: dict) -> dict:
''' Reads a DataFrame with cycling data and determines which units have been used and returns these in a dictionary'''
if options['kind'] == 'batsmall':
time = df.columns[0].split()[-1].strip('[]') time = df.columns[0].split()[-1].strip('[]')
voltage = df.columns[1].split()[-1].strip('[]') voltage = df.columns[1].split()[-1].strip('[]')
current = df.columns[2].split()[-1].strip('[]') current = df.columns[2].split()[-1].strip('[]')
capacity, mass = df.columns[4].split()[-1].strip('[]').split('/') capacity, mass = df.columns[4].split()[-1].strip('[]').split('/')
old_units = {'time': time, 'current': current, 'voltage': voltage, 'capacity': capacity, 'mass': mass} old_units = {'time': time, 'current': current, 'voltage': voltage, 'capacity': capacity, 'mass': mass}
if kind=='neware': if options['kind']=='neware':
for column in df.columns: for column in df.columns:
if 'Voltage' in column: if 'Voltage' in column:
voltage = column.split('(')[-1].strip(')') voltage = column.split('(')[-1].strip(')')
@ -514,7 +518,7 @@ def get_old_units(df, kind):
old_units = {'voltage': voltage, 'current': current, 'capacity': capacity, 'energy': energy} old_units = {'voltage': voltage, 'current': current, 'capacity': capacity, 'energy': energy}
if kind=='biologic': if options['kind'] == 'biologic':
for column in df.columns: for column in df.columns:
if 'time' in column: if 'time' in column:
@ -530,8 +534,6 @@ def get_old_units(df, kind):
old_units = {'voltage': voltage, 'current': current, 'capacity': capacity, 'energy': energy, 'time': time} old_units = {'voltage': voltage, 'current': current, 'capacity': capacity, 'energy': energy, 'time': time}
return old_units return old_units
def convert_time_string(time_string, unit='ms'): def convert_time_string(time_string, unit='ms'):

107
nafuma/electrochemistry/plot.py
View file

@ -6,58 +6,57 @@ import numpy as np
import math import math
import nafuma.electrochemistry as ec import nafuma.electrochemistry as ec
import nafuma.plotting as btp
import nafuma.auxillary as aux
def plot_gc(path, kind, options=None): def plot_gc(data, options=None):
# Prepare plot, and read and process data
fig, ax = prepare_gc_plot(options=options)
cycles = ec.io.read_data(path=path, kind=kind, options=options)
# Update options # Update options
required_options = ['x_vals', 'y_vals', 'which_cycles', 'chg', 'dchg', 'colours', 'differentiate_charge_discharge', 'gradient'] required_options = ['x_vals', 'y_vals', 'which_cycles', 'charge', 'discharge', 'colours', 'differentiate_charge_discharge', 'gradient', 'rc_params', 'format_params']
default_options = {'x_vals': 'capacity', 'y_vals': 'voltage', 'which_cycles': 'all', 'chg': True, 'dchg': True, 'colours': None, 'differentiate_charge_discharge': True, 'gradient': False}
default_options = {
'x_vals': 'capacity', 'y_vals': 'voltage',
'which_cycles': 'all',
'charge': True, 'discharge': True,
'colours': None,
'differentiate_charge_discharge': True,
'gradient': False,
'rc_params': {},
'format_params': {}}
options = update_options(options=options, required_options=required_options, default_options=default_options) options = aux.update_options(options=options, required_options=required_options, default_options=default_options)
# Prepare plot, and read and process data
fig, ax = btp.prepare_plot(options=options)
data['cycles'] = ec.io.read_data(data=data, options=options)
# Update list of cycles to correct indices # Update list of cycles to correct indices
update_cycles_list(cycles=cycles, options=options) update_cycles_list(cycles=data['cycles'], options=options)
colours = generate_colours(cycles=cycles, options=options) colours = generate_colours(cycles=data['cycles'], options=options)
for i, cycle in enumerate(cycles): for i, cycle in enumerate(data['cycles']):
if i in options['which_cycles']: if i in options['which_cycles']:
if options['chg']: if options['charge']:
cycle[0].plot(x=options['x_vals'], y=options['y_vals'], ax=ax, c=colours[i][0]) cycle[0].plot(x=options['x_vals'], y=options['y_vals'], ax=ax, c=colours[i][0])
if options['dchg']: if options['discharge']:
cycle[1].plot(x=options['x_vals'], y=options['y_vals'], ax=ax, c=colours[i][1]) cycle[1].plot(x=options['x_vals'], y=options['y_vals'], ax=ax, c=colours[i][1])
fig, ax = prettify_gc_plot(fig=fig, ax=ax, options=options) fig, ax = btp.adjust_plot(fig=fig, ax=ax, options=options)
return cycles, fig, ax return data['cycles'], fig, ax
def update_options(options, required_options, default_options):
if not options:
options = default_options
else: def update_cycles_list(cycles, options: dict) -> None:
for option in required_options:
if option not in options.keys():
options[option] = default_options[option]
return options
def update_cycles_list(cycles, options):
if not options:
options['which_cycles']
if options['which_cycles'] == 'all': if options['which_cycles'] == 'all':
options['which_cycles'] = [i for i in range(len(cycles))] options['which_cycles'] = [i for i in range(len(cycles))]
@ -81,52 +80,6 @@ def update_cycles_list(cycles, options):
options['which_cycles'] = [i-1 for i in range(which_cycles[0], which_cycles[1]+1)] options['which_cycles'] = [i-1 for i in range(which_cycles[0], which_cycles[1]+1)]
return options
def prepare_gc_plot(options=None):
# First take care of the options for plotting - set any values not specified to the default values
required_options = ['columns', 'width', 'height', 'format', 'dpi', 'facecolor']
default_options = {'columns': 1, 'width': 14, 'format': 'golden_ratio', 'dpi': None, 'facecolor': 'w'}
# If none are set at all, just pass the default_options
if not options:
options = default_options
options['height'] = options['width'] * (math.sqrt(5) - 1) / 2
options['figsize'] = (options['width'], options['height'])
# If options is passed, go through to fill out the rest.
else:
# Start by setting the width:
if 'width' not in options.keys():
options['width'] = default_options['width']
# Then set height - check options for format. If not given, set the height to the width scaled by the golden ratio - if the format is square, set the same. This should possibly allow for the tweaking of custom ratios later.
if 'height' not in options.keys():
if 'format' not in options.keys():
options['height'] = options['width'] * (math.sqrt(5) - 1) / 2
elif options['format'] == 'square':
options['height'] = options['width']
options['figsize'] = (options['width'], options['height'])
# After height and width are set, go through the rest of the options to make sure that all the required options are filled
for option in required_options:
if option not in options.keys():
options[option] = default_options[option]
fig, ax = plt.subplots(figsize=(options['figsize']), dpi=options['dpi'], facecolor=options['facecolor'])
linewidth = 1*options['columns']
axeswidth = 3*options['columns']
plt.rc('lines', linewidth=linewidth)
plt.rc('axes', linewidth=axeswidth)
return fig, ax
def prettify_gc_plot(fig, ax, options=None): def prettify_gc_plot(fig, ax, options=None):
@ -166,7 +119,7 @@ def prettify_gc_plot(fig, ax, options=None):
'title': None 'title': None
} }
update_options(options, required_options, default_options) aux.update_options(options, required_options, default_options)
################################################################## ##################################################################