Merge branch 'master' of https://github.uio.no/rasmusvt/beamtime

beamtime/electrochemistry/__init__.py

@@ -1 +1 @@
-from . import io, plot
+from . import io, plot, unit_tables

beamtime/electrochemistry/io.py

@@ -1,10 +1,27 @@
 import pandas as pd
 import numpy as np
 import matplotlib.pyplot as plt
+import os
 
 
-def read_battsmall(path):
+def read_data(path, kind, options=None):
-	''' Reads BATTSMALL-data into a DataFrame.
+
+	if kind == 'neware':
+		df = read_neware(path)
+		cycles = process_neware_data(df, options=options)
+
+	elif kind == 'batsmall':
+		df = read_batsmall(path)
+		cycles = process_batsmall_data(df=df, options=options)
+
+	elif kind == 'biologic':
+		df = read_biologic(path)
+		cycles = process_biologic_data(df=df, options=options)
+
+	return cycles
+
+def read_batsmall(path):
+	''' Reads BATSMALL-data into a DataFrame.
 
 	Input:
 	path (required): string with path to datafile
@@ -20,31 +37,55 @@ def read_battsmall(path):
 
 
 
-def read_neware(path, summary=False, active_material_weight=None, molecular_weight=None):
+def read_neware(path, summary=False):
-    ''' Reads electrochemistry data, currently only from the Neware battery cycler. Will convert to .csv if the filetype is .xlsx,
+	''' Reads electrochemistry data, currently only from the Neware battery cycler. Will convert to .csv if the filetype is .xlsx,
-    which is the file format the Neware provides for the backup data. In this case it matters if summary is False or not. If file
+	which is the file format the Neware provides for the backup data. In this case it matters if summary is False or not. If file
-    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
 
-    # Convert from .xlsx to .csv to make readtime faster
+	# Convert from .xlsx to .csv to make readtime faster
-    if filename.split('.')[-1] == 'xlsx':
+	if path.split('.')[-1] == 'xlsx':
-        csv_details = ''.join(filename.split('.')[:-1]) + '_details.csv'
+		csv_details = ''.join(path.split('.')[:-1]) + '_details.csv'
-        csv_summary = ''.join(filename.split('.')[:-1]) + '_summary.csv'
+		csv_summary = ''.join(path.split('.')[:-1]) + '_summary.csv'
 
-        Xlsx2csv(filename, outputencoding="utf-8").convert(csv_summary, sheetid=3)
+		if not os.path.isfile(csv_summary):
-        Xlsx2csv(filename, outputencoding="utf-8").convert(csv_details, sheetid=4)
+			Xlsx2csv(path, outputencoding="utf-8").convert(csv_summary, sheetid=3)
-    
-        if summary:
-            df = pd.read_csv(csv_summary)
-        else:
-            df = pd.read_csv(csv_details)
 
-    elif filename.split('.')[-1] == 'csv':
+		if not os.path.isfile(csv_details):
+			Xlsx2csv(path, outputencoding="utf-8").convert(csv_details, sheetid=4)
 
-        df = pd.read_csv(filename)
+		if summary:
-    
+			df = pd.read_csv(csv_summary)
-    
+		else:
-    return df
+			df = pd.read_csv(csv_details)
+
+	elif path.split('.')[-1] == 'csv':
+		df = pd.read_csv(path)
+
+
+	return df
+
+
+
+def read_biologic(path):
+	''' Reads Bio-Logic-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.'''
+
+	with open(path, 'r') as f:
+		lines = f.readlines()
+
+	header_lines = int(lines[1].split()[-1]) - 1
+	
+
+	df = pd.read_csv(path, sep='\t', skiprows=header_lines)
+	df.dropna(inplace=True, axis=1)
+
+	return df
 
 
 
@@ -52,16 +93,14 @@ def read_neware(path, summary=False, active_material_weight=None, molecular_weig
 
 
 
-#def process_battsmall_data(df, t='ms', C='mAh/g', I='mA', U='V'):
+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.
-def process_battsmall_data(df, units=None, splice_cycles=None, molecular_weight=None):
-	''' Takes BATTSMALL-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.
 
 	For this to work, the cycling program must be set to use the counter.
 
 	Input:
-	df (required): A pandas DataFrame containing BATTSMALL-data, as obtained from read_battsmall().
+	df (required): A pandas DataFrame containing BATSMALL-data, as obtained from read_batsmall().
 	t (optional): Unit for time data. Defaults to ms.
 	C (optional): Unit for specific capacity. Defaults to mAh/g.
 	I (optional): Unit for current. Defaults mA.
@@ -71,51 +110,42 @@ def process_battsmall_data(df, units=None, splice_cycles=None, molecular_weight=
 	cycles: A list with 
 	'''
 
-	#########################
+	required_options = ['splice_cycles', 'molecular_weight', 'reverse_discharge', 'units']
-	#### UNIT CONVERSION ####
+	default_options = {'splice_cycles': None, 'molecular_weight': None, 'reverse_discharge': False, 'units': None}
-	#########################
 
-	# Complete the list of units - if not all are passed, then default value will be used
+	if not options:
-	required_units = ['t', 'I', 'U', 'C']
+		options = default_options
-	default_units = {'t': 'h', 'I': 'mA', 'U': 'V', 'C': 'mAh/g'}
+	else:
+		for option in required_options:
+			if option not in options.keys():
+				options[option] = default_options[option]
 
-	if not units:
-		units = default_units
 
-	if units:
+	# Complete set of new units and get the units used in the dataset, and convert values in the DataFrame from old to new.
-		for unit in required_units:
+	new_units = set_units(units=options['units'])
-			if unit not in units.values():
+	old_units = get_old_units(df, kind='batsmall')
-				units[unit] = default_units[unit]
+	df = unit_conversion(df=df, new_units=new_units, old_units=old_units, kind='batsmall')
-		
-	
-	# Get the units used in the data set
-	t_prev = df.columns[0].split()[-1].strip('[]')
-	U_prev = df.columns[1].split()[-1].strip('[]')
-	I_prev = df.columns[2].split()[-1].strip('[]')
-	C_prev, m_prev = df.columns[4].split()[-1].strip('[]').split('/')
-	prev_units = {'t': t_prev, 'I': I_prev, 'U': U_prev, 'C': C_prev}
 
-	# Convert all units to the desired units.
+	options['units'] = new_units
-	df = unit_conversion(df=df, units=units)
 
 	# 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': ''})
-	df = df[df["Comment"].str.contains("program")==False]
+	df = df[df["comment"].str.contains("program")==False]
 
 	# Creates masks for charge and discharge curves
-	chg_mask = df['I'] >= 0
+	chg_mask = df['current'] >= 0
-	dchg_mask = df['I'] < 0
+	dchg_mask = df['current'] < 0
 
 	# Initiate cycles list
 	cycles = []
 
 	# Loop through all the cycling steps, change the current and capacities in the 
-	for i in range(df["Z1"].max()):
+	for i in range(df["count"].max()):
 
-		sub_df = df.loc[df['Z1'] == i].copy()
+		sub_df = df.loc[df['count'] == i].copy()
 
-		sub_df.loc[dchg_mask, 'I']  *= -1
+		sub_df.loc[dchg_mask, 'current']  *= -1
-		sub_df.loc[dchg_mask, 'C'] *= -1
+		sub_df.loc[dchg_mask, 'specific_capacity'] *= -1
 
 		chg_df = sub_df.loc[chg_mask]
 		dchg_df = sub_df.loc[dchg_mask]
@@ -124,6 +154,18 @@ def process_battsmall_data(df, units=None, splice_cycles=None, molecular_weight=
 		if chg_df.empty and dchg_df.empty:
 			continue
 
+		if options['reverse_discharge']:
+			max_capacity = dchg_df['capacity'].max() 
+			dchg_df['capacity'] = np.abs(dchg_df['capacity'] - max_capacity)
+
+			if 'specific_capacity' in df.columns:
+				max_capacity = dchg_df['specific_capacity'].max() 
+				dchg_df['specific_capacity'] = np.abs(dchg_df['specific_capacity'] - max_capacity)
+
+				if 'ions' in df.columns:
+					max_capacity = dchg_df['ions'].max() 
+					dchg_df['ions'] = np.abs(dchg_df['ions'] - max_capacity)
+
 		cycles.append((chg_df, dchg_df))
 
 
@@ -132,99 +174,312 @@ def process_battsmall_data(df, units=None, splice_cycles=None, molecular_weight=
 	return cycles
 
 
-def process_neware_data(df, units=None, splice_cycles=None, active_material_weight=None, molecular_weight=None):
+def process_neware_data(df, options=None):
 
-	#########################
+	""" Takes data from NEWARE in a DataFrame as read by read_neware() and converts units, adds columns and splits into cycles.
-	#### UNIT CONVERSION ####
+	
-	#########################
+	Input:
+	df: pandas DataFrame containing NEWARE data as read by read_neware()
+	units: dictionary containing the desired units. keywords: capacity, current, voltage, mass, energy, time
+	splice_cycles: tuple containing index of cycles that should be spliced. Specifically designed to add two charge steps during the formation cycle with two different max voltages
+	active_materiale_weight: weight of the active material (in mg) used in the cell. 
+	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']
+	default_options = {'units': None, 'active_material_weight': None, 'molecular_weight': None, 'reverse_discharge': False, 'splice_cycles': None}
+
+	if not options:
+		options = default_options
+	else:
+		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.
+	new_units = set_units(units=options['units'])
+	old_units = get_old_units(df=df, kind='neware')
+	
+	df = add_columns(df=df, active_material_weight=options['active_material_weight'], molecular_weight=options['molecular_weight'], old_units=old_units, kind='neware')
+
+	df = unit_conversion(df=df, new_units=new_units, old_units=old_units, kind='neware')
+
+	options['units'] = new_units
+
+
+	# Creates masks for charge and discharge curves
+	chg_mask = df['status'] == 'CC Chg'
+	dchg_mask = df['status'] == 'CC DChg'
+
+	# Initiate cycles list
+	cycles = []
+
+	# Loop through all the cycling steps, change the current and capacities in the 
+	for i in range(df["cycle"].max()):
+
+		sub_df = df.loc[df['cycle'] == i].copy()
+
+		#sub_df.loc[dchg_mask, 'current']  *= -1
+		#sub_df.loc[dchg_mask, 'capacity'] *= -1
+
+		chg_df = sub_df.loc[chg_mask]
+		dchg_df = sub_df.loc[dchg_mask]
+
+		# Continue to next iteration if the charge and discharge DataFrames are empty (i.e. no current)
+		if chg_df.empty and dchg_df.empty:
+			continue
+
+		if options['reverse_discharge']:
+			max_capacity = dchg_df['capacity'].max() 
+			dchg_df['capacity'] = np.abs(dchg_df['capacity'] - max_capacity)
+
+			if 'specific_capacity' in df.columns:
+				max_capacity = dchg_df['specific_capacity'].max() 
+				dchg_df['specific_capacity'] = np.abs(dchg_df['specific_capacity'] - max_capacity)
+
+				if 'ions' in df.columns:
+					max_capacity = dchg_df['ions'].max() 
+					dchg_df['ions'] = np.abs(dchg_df['ions'] - max_capacity)
+
+		cycles.append((chg_df, dchg_df))
+
+
+
+	return cycles
+
+
+def process_biologic_data(df, options=None):
+
+	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}
+
+	if not options:
+		options = default_options
+	else:
+		for option in required_options:
+			if option not in options.keys():
+				options[option] = default_options[option]
+
+	# 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()
+
+	# 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'])
+	old_units = get_old_units(df=df, kind='biologic')
+	
+	df = add_columns(df=df, active_material_weight=options['active_material_weight'], molecular_weight=options['molecular_weight'], old_units=old_units, kind='biologic')
+
+	df = unit_conversion(df=df, new_units=new_units, old_units=old_units, kind='biologic')
+
+	options['units'] = new_units
+
+
+	# Creates masks for charge and discharge curves
+	chg_mask = (df['status'] == 1) & (df['status_change'] != 1)
+	dchg_mask = (df['status'] == 2) & (df['status_change'] != 1)
+
+
+
+	# Initiate cycles list
+	cycles = []
+
+	# Loop through all the cycling steps, change the current and capacities in the 
+	for i in range(int(df["cycle"].max())):
+
+		sub_df = df.loc[df['cycle'] == i].copy()
+
+		#sub_df.loc[dchg_mask, 'current']  *= -1
+		#sub_df.loc[dchg_mask, 'capacity'] *= -1
+
+		chg_df = sub_df.loc[chg_mask]
+		dchg_df = sub_df.loc[dchg_mask]
+
+		# Continue to next iteration if the charge and discharge DataFrames are empty (i.e. no current)
+		if chg_df.empty and dchg_df.empty:
+			continue
+
+		if options['reverse_discharge']:
+			max_capacity = dchg_df['capacity'].max() 
+			dchg_df['capacity'] = np.abs(dchg_df['capacity'] - max_capacity)
+
+			if 'specific_capacity' in df.columns:
+				max_capacity = dchg_df['specific_capacity'].max() 
+				dchg_df['specific_capacity'] = np.abs(dchg_df['specific_capacity'] - max_capacity)
+
+				if 'ions' in df.columns:
+					max_capacity = dchg_df['ions'].max() 
+					dchg_df['ions'] = np.abs(dchg_df['ions'] - max_capacity)
+
+		cycles.append((chg_df, dchg_df))
+
+
+
+	return cycles
+
+
+def add_columns(df, active_material_weight, molecular_weight, old_units, kind):
+
+	if kind == 'neware':
+		if active_material_weight:
+			df["SpecificCapacity({}/mg)".format(old_units["capacity"])] = df["Capacity({})".format(old_units['capacity'])] / (active_material_weight)
+
+			if molecular_weight:
+				faradays_constant = 96485.3365 # [F] = C mol^-1 = As mol^-1
+				seconds_per_hour = 3600 # s h^-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
+
+
+	if kind == 'biologic':
+		if active_material_weight:
+
+			capacity = old_units['capacity'].split('h')[0] + '.h'
+
+
+			df["SpecificCapacity({}/mg)".format(old_units["capacity"])] = df["Capacity/{}".format(capacity)] / (active_material_weight)
+
+			if molecular_weight:
+				faradays_constant = 96485.3365 # [F] = C mol^-1 = As mol^-1
+				seconds_per_hour = 3600 # s h^-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
+
+	return df
+
+
+def unit_conversion(df, new_units, old_units, kind):
+	from . import unit_tables
+
+	if 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["U [{}]".format(old_units["voltage"])] = df["U [{}]".format(old_units["voltage"])] * unit_tables.voltage()[old_units["voltage"]].loc[new_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["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.columns = ['time', 'voltage', 'current', 'count', 'specific_capacity', 'comment']
+
+
+	if 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['Voltage({})'.format(old_units['voltage'])] = df['Voltage({})'.format(old_units['voltage'])] * unit_tables.voltage()[old_units['voltage']].loc[new_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['Energy({})'.format(old_units['energy'])] = df['Energy({})'.format(old_units['energy'])] * unit_tables.energy()[old_units['energy']].loc[new_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['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)
+		columns = ['status', 'jump', 'cycle', 'steps', 'current', 'voltage', 'capacity', 'energy']
+
+		if 'SpecificCapacity({}/mg)'.format(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"]]
+			columns.append('specific_capacity')
+
+			if 'IonsExtracted' in df.columns:
+				columns.append('ions')
+
+
+
+		columns.append('cycle_time')
+		columns.append('run_time')
+
+
+		df.drop(['Record number', 'Relative Time(h:min:s.ms)', 'Real Time(h:min:s.ms)'], axis=1, inplace=True)
+
+		df.columns = columns
+
+	if 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["Ewe/{}".format(old_units["voltage"])] = df["Ewe/{}".format(old_units["voltage"])] * unit_tables.voltage()[old_units["voltage"]].loc[new_units['voltage']]
+		df["<I>/{}".format(old_units["current"])] = df["<I>/{}".format(old_units["current"])] * unit_tables.current()[old_units["current"]].loc[new_units['current']]
+		
+		capacity = 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"]])
+
+		columns = ['status_change', 'status', 'time', 'voltage', 'energy_charge', 'energy_discharge', 'current', 'capacity', 'cycle']
+
+		if 'SpecificCapacity({}/mg)'.format(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"]]
+			columns.append('specific_capacity')
+
+			if 'IonsExtracted' in df.columns:
+				columns.append('ions')
+
+		df.columns = columns
+
+	return df
+
+
+def set_units(units=None):
 	
 	# Complete the list of units - if not all are passed, then default value will be used
-	required_units = ['t', 'I', 'U', 'C']
+	required_units = ['time', 'current', 'voltage', 'capacity', 'mass', 'energy', 'specific_capacity']
-	default_units = {'t': 'h', 'I': 'mA', 'U': 'V', 'C': 'mAh/g'}
+	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.values():
+			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':
+		time = df.columns[0].split()[-1].strip('[]')
+		voltage = df.columns[1].split()[-1].strip('[]')
+		current = df.columns[2].split()[-1].strip('[]')
+		capacity, mass = df.columns[4].split()[-1].strip('[]').split('/')
+		old_units = {'time': time, 'current': current, 'voltage': voltage, 'capacity': capacity, 'mass': mass}
+
+	if kind=='neware':
+		
+		for column in df.columns:
+			if 'Voltage' in column:
+				voltage = column.split('(')[-1].strip(')')
+			elif 'Current' in column:
+				current = column.split('(')[-1].strip(')')
+			elif 'Capacity' in column:
+				capacity = column.split('(')[-1].strip(')')
+			elif 'Energy' in column:
+				energy = column.split('(')[-1].strip(')')
+
+		old_units = {'voltage': voltage, 'current': current, 'capacity': capacity, 'energy': energy}
+
+
+	if kind=='biologic':
+
+		for column in df.columns:
+			if 'time' in column:
+				time = column.split('/')[-1]
+			elif 'Ewe' in column:
+				voltage = column.split('/')[-1]
+			elif 'Capacity' in column:
+				capacity = column.split('/')[-1].replace('.', '')
+			elif 'Energy' in column:
+				energy = column.split('/')[-1].replace('.', '')
+			elif '<I>' in column:
+				current = column.split('/')[-1]
+
+		old_units = {'voltage': voltage, 'current': current, 'capacity': capacity, 'energy': energy, 'time': time}
 	
 
-	# Get the units used in the data set
-	t_prev = 's' # default in 
-	U_prev = df.columns[1].split()[-1].strip('[]')
-	I_prev = df.columns[2].split()[-1].strip('[]')
-	C_prev, m_prev = df.columns[4].split()[-1].strip('[]').split('/')
-	prev_units = {'t': t_prev, 'I': I_prev, 'U': U_prev, 'C': C_prev}
-
-	# Convert all units to the desired units.
-	df = unit_conversion(df=df, units=units)
-
-
-
-	if active_material_weight:
-		df["SpecificCapacity(mAh/g)"] = df["Capacity(mAh)"] / (active_material_weight / 1000)
-
-	if molecular_weight:
-		faradays_constant = 96485.3365 # [F] = C mol^-1 = As mol^-1
-		seconds_per_hour = 3600 # s h^-1
-		f = faradays_constant / seconds_per_hour * 1000.0 # [f] = mAh mol^-1
-
-		df["IonsExtracted"] = (df["SpecificCapacity(mAh/g)"]*molecular_weight)/f
-
-
-def unit_conversion(df, units, prev_units, kind):
-
-	C, m = units['C'].split('/')
-	C_prev, m_prev = prev_units['C'].split('/')
-
-
-	# Define matrix for unit conversion for time
-	t_units_df = {'h': [1, 60, 3600, 3600000], 'min': [1/60, 1, 60, 60000], 's': [1/3600, 1/60, 1, 1000], 'ms': [1/3600000, 1/60000, 1/1000, 1]}
-	t_units_df = pd.DataFrame(t_units_df)
-	t_units_df.index = ['h', 'min', 's', 'ms']
-
-	# Define matrix for unit conversion for current
-	I_units_df = {'A': [1, 1000, 1000000], 'mA': [1/1000, 1, 1000], 'uA': [1/1000000, 1/1000, 1]}
-	I_units_df = pd.DataFrame(I_units_df)
-	I_units_df.index = ['A', 'mA', 'uA']
-
-	# Define matrix for unit conversion for voltage
-	U_units_df = {'V': [1, 1000, 1000000], 'mV': [1/1000, 1, 1000], 'uV': [1/1000000, 1/1000, 1]}
-	U_units_df = pd.DataFrame(U_units_df)
-	U_units_df.index = ['V', 'mV', 'uV']
-
-	# Define matrix for unit conversion for capacity
-	C_units_df = {'Ah': [1, 1000, 1000000], 'mAh': [1/1000, 1, 1000], 'uAh': [1/1000000, 1/1000, 1]}
-	C_units_df = pd.DataFrame(C_units_df)
-	C_units_df.index = ['Ah', 'mAh', 'uAh']
-
-	# Define matrix for unit conversion for capacity
-	m_units_df = {'kg': [1, 1000, 1000000, 1000000000], 'g': [1/1000, 1, 1000, 1000000], 'mg': [1/1000000, 1/1000, 1, 1000], 'ug': [1/1000000000, 1/1000000, 1/1000, 1]}
-	m_units_df = pd.DataFrame(m_units_df)
-	m_units_df.index = ['kg', 'g', 'mg', 'ug']
-
-	#print(df["TT [{}]".format(t_prev)])
-	df["TT [{}]".format(t_prev)] = df["TT [{}]".format(t_prev)] * t_units_df[t_prev].loc[units['t']]
-	df["U [{}]".format(U_prev)] = df["U [{}]".format(U_prev)] * U_units_df[U_prev].loc[units['U']]
-	df["I [{}]".format(I_prev)] = df["I [{}]".format(I_prev)] * I_units_df[I_prev].loc[units['I']]
-	df["C [{}/{}]".format(C_prev, m_prev)] = df["C [{}/{}]".format(C_prev, m_prev)] * (C_units_df[C_prev].loc[C] / m_units_df[m_prev].loc[m])
-
-	df.columns = ['TT', 'U', 'I', 'Z1', 'C', 'Comment']
-
-
-
-	return df
-
 
+	return old_units
 
 def convert_time_string(time_string, unit='ms'):
 	''' Convert time string from Neware-data with the format hh:mm:ss.xx to any given unit'''
 
 	h, m, s = time_string.split(':')  
-	ms = int(s)*1000 + int(m)*1000*60 + int(h)*1000*60*60
+	ms = float(s)*1000 + int(m)*1000*60 + int(h)*1000*60*60
 
 	factors = {'ms': 1, 's': 1/1000, 'min': 1/(1000*60), 'h': 1/(1000*60*60)}
 
@@ -240,25 +495,26 @@ def convert_datetime_string(datetime_string, reference, unit='s'):
 	from datetime import datetime
 
 	# Parse the 
-	cur_date, cur_time = datetime_string.split()
+	current_date, current_time = datetime_string.split()
-	cur_y, cur_mo, cur_d = cur_date.split('-')
+	current_year, current_month, current_day = current_date.split('-')
-	cur_h, cur_m, cur_s = cur_time.split(':')
+	current_hour, current_minute, current_second = current_time.split(':')
-	cur_date = datetime(int(cur_y), int(cur_mo), int(cur_d), int(cur_h), int(cur_m), int(cur_s))
+	current_date = datetime(int(current_year), int(current_month), int(current_day), int(current_hour), int(current_minute), int(current_second))
 
-	ref_date, ref_time = reference.split()
+	reference_date, reference_time = reference.split()
-	ref_y, ref_mo, ref_d = ref_date.split('-')
+	reference_year, reference_month, reference_day = reference_date.split('-')
-	ref_h, ref_m, ref_s = ref_time.split(':')
+	reference_hour, reference_minute, reference_second = reference_time.split(':')
-	ref_date = datetime(int(ref_y), int(ref_mo), int(ref_d), int(ref_h), int(ref_m), int(ref_s))
+	reference_date = datetime(int(reference_year), int(reference_month), int(reference_day), int(reference_hour), int(reference_minute), int(reference_second))
 
-	days = cur_date - ref_date
+	days = current_date - reference_date
 
-	s = days.seconds
+
+	s = days.days*24*60*60 + days.seconds
 
 	factors = {'ms': 1000, 's': 1, 'min': 1/(60), 'h': 1/(60*60)}
 
-	t = s * factors[unit]
+	time = s * factors[unit]
 
-	return t
+	return time
 
 def splice_cycles(first, second):
 

beamtime/electrochemistry/plot.py

@@ -1,40 +1,373 @@
 import matplotlib.pyplot as plt
+from matplotlib.ticker import (MultipleLocator, FormatStrFormatter,AutoMinorLocator)
+
 import pandas as pd
 import numpy as np
+import math
+
+import beamtime.electrochemistry as ec
 
 
-def plot_gc(cycles, which_cycles='all', chg=True, dchg=True, colours=None, x='C', y='U'):
+def plot_gc(path, kind, options=None):
 
-	fig, ax = prepare_gc_plot()
+	# 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)
 
 
-	if which_cycles == 'all':
+	# Update options
-		which_cycles = [i for i, c in enumerate(cycles)]
+	required_options = ['x_vals', 'y_vals', 'which_cycles', 'chg', 'dchg', 'colours', 'gradient']
+	default_options = {'x_vals': 'capacity', 'y_vals': 'voltage', 'which_cycles': 'all', 'chg': True, 'dchg': True, 'colours': None, 'gradient': False}
 
-	if not colours:
+	options = update_options(options=options, required_options=required_options, default_options=default_options)
-		chg_colour = (40/255, 70/255, 75/255) # Dark Slate Gray #28464B
+
-		dchg_colour = (239/255, 160/255, 11/255) # Marigold #EFA00B
+	# Update list of cycles to correct indices
+	update_cycles_list(cycles=cycles, options=options)
+
+	colours = generate_colours(cycles=cycles, options=options)
+
+	print(len(options['which_cycles']))
+	print(len(colours))
+
+
+
+	for i, cycle in enumerate(cycles):
+		if i in options['which_cycles']:
+			if options['chg']:
+				cycle[0].plot(x=options['x_vals'], y=options['y_vals'], ax=ax, c=colours[i][0])
+
+			if options['dchg']:
+				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)
+
+	return cycles, fig, ax
+
+
+def update_options(options, required_options, default_options):
+
+	if not options:
+		options = default_options
+	
+	else:
+		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':
+		options['which_cycles'] = [i for i in range(len(cycles))]
+
+
+	elif type(options['which_cycles']) == list:
+		options['which_cycles'] = [i-1 for i in options['which_cycles']]
 	
 	
+	# Tuple is used to define an interval - as elements tuples can't be assigned, I convert it to a list here.
+	elif type(options['which_cycles']) == tuple:
+		which_cycles = list(options['which_cycles'])
 
-	for i, cycle in cycles:
+		if which_cycles[0] <= 0:
-		if i in which_cycles:
+			which_cycles[0] = 1
-			if chg:
+
-				cycle[0].plot(ax=ax)
+		elif which_cycles[1] < 0:
+			which_cycles[1] = len(cycles)
+
+
+		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):
+
+
+	##################################################################
+	######################### UPDATE OPTIONS #########################
+	##################################################################
+
+	# Define the required options
+	required_options = [
+	'columns', 
+	'xticks', 'yticks', 
+	'show_major_ticks',
+	'show_minor_ticks',
+	'xlim', 'ylim',
+	'hide_x_axis', 'hide_y_axis', 
+	'x_vals', 'y_vals', 
+	'xlabel', 'ylabel', 
+	'units', 'sizes',
+	'title'
+	]
+
+
+	# Define the default options
+	default_options = {
+		'columns': 1,
+		'xticks': None,
+		'yticks': None,
+		'show_major_ticks': [True, True, True, True],
+		'show_minor_ticks': [True, True, True, True],
+		'xlim': None,
+		'ylim': None,
+		'hide_x_axis': False,
+		'hide_y_axis': False,
+		'x_vals': 'specific_capacity',
+		'y_vals': 'voltage',
+		'xlabel': None,
+		'ylabel': None,
+		'units': None,
+		'sizes': None,
+		'title': None 	
+	}
+
+	update_options(options, required_options, default_options)
+
+
+	##################################################################
+	########################## DEFINE SIZES ##########################
+	##################################################################
+
+	# Define the required sizes
+	required_sizes = [
+		'labels', 
+		'legend', 
+		'title', 
+		'line', 'axes', 
+		'tick_labels', 
+		'major_ticks', 'minor_ticks']
+	
+	
+	
+	# Define default sizes
+	default_sizes = {
+			'labels': 30*options['columns'],
+			'legend': 30*options['columns'],
+			'title': 30*options['columns'],
+			'line': 3*options['columns'],
+			'axes': 3*options['columns'],
+			'tick_labels': 30*options['columns'],
+			'major_ticks': 20*options['columns'],
+			'minor_ticks': 10*options['columns']	
+	}
+	
+	# Initialise dictionary if it doesn't exist
+	if not options['sizes']:
+		options['sizes'] = {}
+
+
+	# Update dictionary with default values where none is supplied
+	for size in required_sizes:
+		if size not in options['sizes']:
+			options['sizes'][size] = default_sizes[size]
+
+
+	##################################################################
+	########################## AXIS LABELS ###########################
+	##################################################################
+
+
+	if not options['xlabel']:
+		print(options['x_vals'])
+		print(options['units'])
+		options['xlabel'] = prettify_labels(options['x_vals']) + ' [{}]'.format(options['units'][options['x_vals']])
+	
+	else:
+		options['xlabel'] = options['xlabel'] + ' [{}]'.format(options['units'][options['x_vals']])
+
+
+	if not options['ylabel']:
+		options['ylabel'] = prettify_labels(options['y_vals']) + ' [{}]'.format(options['units'][options['y_vals']])
+	
+	else:
+		options['ylabel'] = options['ylabel'] + ' [{}]'.format(options['units'][options['y_vals']])
+
+	ax.set_xlabel(options['xlabel'], size=options['sizes']['labels'])
+	ax.set_ylabel(options['ylabel'], size=options['sizes']['labels'])
+
+	##################################################################
+	###################### TICK MARKS & LABELS #######################
+	##################################################################
+
+	ax.tick_params(direction='in', which='major', bottom=options['show_major_ticks'][0], left=options['show_major_ticks'][1], top=options['show_major_ticks'][2], right=options['show_major_ticks'][0], length=options['sizes']['major_ticks'], width=options['sizes']['axes'])
+	ax.tick_params(direction='in', which='minor', bottom=options['show_minor_ticks'][0], left=options['show_minor_ticks'][1], top=options['show_minor_ticks'][2], right=options['show_minor_ticks'][0], length=options['sizes']['minor_ticks'], width=options['sizes']['axes'])
 
 
 
+	# DEFINE AND SET TICK DISTANCES
+
+	default_ticks = {
+		'specific_capacity': [100, 50], 
+		'capacity': [0.1, 0.05],
+		'voltage': [0.5, 0.25]
+		}
+
+
+
+	# Set default tick distances for x-axis if not specified
+	if not options['xticks']:
+
+		major_xtick = default_ticks[options['x_vals']][0]
+		minor_xtick = default_ticks[options['x_vals']][1]
+
+	# Otherwise apply user input
+	else:
+		major_xtick = options['xticks'][0]
+		minor_xtick = options['xticks'][1]
+
+
+	# Set default tick distances for x-axis if not specified
+	if not options['yticks']:
+
+		major_ytick = default_ticks[options['y_vals']][0]
+		minor_ytick = default_ticks[options['y_vals']][1]
+
+	# Otherwise apply user input
+	else:
+		major_xtick = options['yticks'][0]
+		minor_xtick = options['yticks'][1]
+
+
+	# Apply values
+	ax.xaxis.set_major_locator(MultipleLocator(major_xtick))
+	ax.xaxis.set_minor_locator(MultipleLocator(minor_xtick))
+
+	ax.yaxis.set_major_locator(MultipleLocator(major_ytick))
+	ax.yaxis.set_minor_locator(MultipleLocator(minor_ytick))
+
+
+	# SET FONTSIZE OF TICK LABELS
+
+	plt.xticks(fontsize=options['sizes']['tick_labels'])
+	plt.yticks(fontsize=options['sizes']['tick_labels'])
+
+	##################################################################
+	############################# TITLE ##############################
+	##################################################################
+
+	if options['title']:
+		ax.set_title(options['title'], size=options['sizes']['title'])
+
+	##################################################################
+	############################# LEGEND #############################
+	##################################################################
+
+	ax.get_legend().remove()
+
+	return fig, ax
 
 	
-
+def prettify_labels(label):
-
-
-
-
-
-def prepare_gc_plot(figsize=(14,7), dpi=None):
-
-	fig, ax = plt.subplots(figsize=figsize, dpi=dpi)
 	
+	labels_dict = {
+		'capacity': 'Capacity',
+		'specific_capacity': 'Specific capacity',
+		'voltage': 'Voltage',
+		'current': 'Current',
+		'energy': 'Energy',
+	}
 
-	return fig, ax
+	return labels_dict[label]
+
+
+
+
+
+
+
+
+def generate_colours(cycles, options):
+
+	# Assign colours from the options dictionary if it is defined, otherwise use standard colours.
+	if options['colours']:
+		charge_colour = options['colours'][0]
+		discharge_colour = options['colours'][1]
+	
+	else:
+		charge_colour = (40/255, 70/255, 75/255) # Dark Slate Gray #28464B, coolors.co
+		discharge_colour = (239/255, 160/255, 11/255) # Marigold #EFA00B, coolors.co
+
+
+
+	# If gradient is enabled, find start and end points for each colour
+	if options['gradient']:
+
+		add_charge = min([(1-x)*0.75 for x in charge_colour])
+		add_discharge = min([(1-x)*0.75 for x in discharge_colour])
+
+		charge_colour_start = charge_colour
+		charge_colour_end = [x+add_charge for x in charge_colour]
+
+		discharge_colour_start = discharge_colour
+		discharge_colour_end = [x+add_discharge for x in discharge_colour]
+
+
+
+	# Generate lists of colours
+	colours = []
+	
+	for cycle_number in range(0, len(cycles)):
+		if options['gradient']:
+			weight_start = (len(cycles) - cycle_number)/len(cycles)
+			weight_end = cycle_number/len(cycles)
+
+			charge_colour = [weight_start*start_colour + weight_end*end_colour for start_colour, end_colour in zip(charge_colour_start, charge_colour_end)]
+			discharge_colour = [weight_start*start_colour + weight_end*end_colour for start_colour, end_colour in zip(discharge_colour_start, discharge_colour_end)]
+
+		colours.append([charge_colour, discharge_colour])
+
+	return colours

beamtime/electrochemistry/unit_tables.py

@@ -0,0 +1,53 @@
+import pandas as pd
+
+def time():
+    # Define matrix for unit conversion for time
+    time = {'h': [1, 60, 3600, 3600000], 'min': [1/60, 1, 60, 60000], 's': [1/3600, 1/60, 1, 1000], 'ms': [1/3600000, 1/60000, 1/1000, 1]}
+    time = pd.DataFrame(time)
+    time.index = ['h', 'min', 's', 'ms']
+
+    return time
+
+def current():
+    # Define matrix for unit conversion for current
+    current = {'A': [1, 1000, 1000000], 'mA': [1/1000, 1, 1000], 'uA': [1/1000000, 1/1000, 1]}
+    current = pd.DataFrame(current)
+    current.index = ['A', 'mA', 'uA']
+
+    return current
+
+def voltage():
+    # Define matrix for unit conversion for voltage
+    voltage = {'V': [1, 1000, 1000000], 'mV': [1/1000, 1, 1000], 'uV': [1/1000000, 1/1000, 1]}
+    voltage = pd.DataFrame(voltage)
+    voltage.index = ['V', 'mV', 'uV']
+
+    return voltage
+
+def capacity():
+    # Define matrix for unit conversion for capacity
+    capacity = {'Ah': [1, 1000, 1000000], 'mAh': [1/1000, 1, 1000], 'uAh': [1/1000000, 1/1000, 1]}
+    capacity = pd.DataFrame(capacity)
+    capacity.index = ['Ah', 'mAh', 'uAh']
+
+    return capacity
+
+def mass():
+    # Define matrix for unit conversion for capacity
+    mass = {'kg': [1, 1000, 1000000, 1000000000], 'g': [1/1000, 1, 1000, 1000000], 'mg': [1/1000000, 1/1000, 1, 1000], 'ug': [1/1000000000, 1/1000000, 1/1000, 1]}
+    mass = pd.DataFrame(mass)
+    mass.index = ['kg', 'g', 'mg', 'ug']
+
+    return mass
+
+
+def energy():
+    
+    energy = {'kWh': [1, 1000, 1000000], 'Wh': [1/1000, 1, 1000], 'mWh': [1/100000, 1/1000, 1]}
+    energy = pd.DataFrame(energy)
+    energy.index = ['kWh', 'Wh', 'mWh']
+
+    return energy
+
+
+