dash_resumable_upload.read_file_dash() - Code Metrics - Inspection of "pylinted everything" - sabiharustam/voltcycle - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( 0c3829...de7c60 )

by Keertana

created 2019-03-22 08:41 UTC

dash_resumable_upload.read_file_dash() C

↳ Parent: dash_resumable_upload

Complexity

Conditions

Size

Total Lines	42
Code Lines	26

Duplication

Lines	42
Ratio	100 %

Importance

Changes

Metric	Value
eloc	26
dl	42
loc	42
rs	6.6666
c	0
b	0
f	0
cc	9
nop	1

# This is a tool to automate cyclic voltametry analysis.
# Current Version = 1

import pandas as pd
import numpy as np
import csv
import matplotlib.pyplot as plt
import warnings
import matplotlib.cbook
import peakutils
import copy
from matplotlib import rcParams


def read_cycle(data):

    """This function reads a segment of datafile (corresponding a cycle)
    and generates a dataframe with columns 'Potential' and 'Current'

    Parameters
    __________
    data: segment of data file

    Returns
    _______
    A dataframe with potential and current columns  
    """     

    current = []
    potential = []
    for i in data[3:]:
        current.append(float(i.split("\t")[4]))
        potential.append(float(i.split("\t")[3]))
    zippedList = list(zip(potential, current))
    df = pd.DataFrame(zippedList, columns = ['Potential' , 'Current'])
    return df


def read_file_dash(lines):

    """This function is exactly similar to read_file, but it is for dash

    Parameters
    __________
    file: lines from dash input file

    Returns:
    ________
    dict_of_df: dictionary of dataframes with keys = cycle numbers and
    values = dataframes for each cycle
    n_cycle: number of cycles in the raw file
    """
    dict_of_df = {}
    h = 0
    l = 0
    n_cycle = 0
    number = 0
    #a = []
    #with open(file, 'rt') as f:
    #    print(file + ' Opened')
    for line in lines:
        record = 0
        if not (h and l):
            if line.startswith('SCANRATE'):
                scan_rate = float(line.split()[2])
                h = 1
            if line.startswith('STEPSIZE'):
                step_size = float(line.split()[2])
                l = 1
        if line.startswith('CURVE'):
            n_cycle += 1
            if n_cycle > 1:
                number = n_cycle - 1
                df = read_cycle(a)
                key_name = 'cycle_' + str(number)
                #key_name = number
                dict_of_df[key_name] = copy.deepcopy(df)
            a = []
        if n_cycle:
            a.append(line)
    return dict_of_df, number


def read_file(file):

    """This function reads the raw data file, gets the scanrate and stepsize
    and then reads the lines according to cycle number. Once it reads the data
    for one cycle, it calls read_cycle function to generate a dataframe. It 
    does the same thing for all the cycles and finally returns a dictionary,
    the keys of which are the cycle numbers and the values are the 
    corresponding dataframes.

    Parameters
    __________
    file: raw data file

    Returns:
    ________
    dict_of_df: dictionary of dataframes with keys = cycle numbers and
    values = dataframes for each cycle
    n_cycle: number of cycles in the raw file  
    """   
    dict_of_df = {} 
    h = 0
    l = 0
    n_cycle = 0
    #a = []
    with open(file, 'rt') as f:
        print(file + ' Opened')
        for line in f:
            record = 0
            if not (h and l):
                if line.startswith('SCANRATE'):
                    scan_rate = float(line.split()[2])
                    h = 1
                if line.startswith('STEPSIZE'):
                    step_size = float(line.split()[2])
                    l = 1
            if line.startswith('CURVE'):
                n_cycle += 1
                if n_cycle > 1:
                    number = n_cycle - 1
                    df = read_cycle(a)
                    key_name = 'cycle_' + str(number)
                    #key_name = number
                    dict_of_df[key_name] = copy.deepcopy(df)
                a = []
            if n_cycle:
                a.append(line)
    return dict_of_df, number


#df = pd.DataFrame(list(dict1['df_1'].items()))
#list1, list2 = list(dict1['df_1'].items())
#list1, list2 = list(dict1.get('df_'+str(1)))

def data_frame(dict_cycle, n):

    """Reads the dictionary of dataframes and returns dataframes for each cycle

    Parameters
    __________
    dict_cycle: Dictionary of dataframes
    n: cycle number

    Returns:
    _______
    Dataframe correcponding to the cycle number 
    """
    list1, list2 = (list(dict_cycle.get('cycle_'+str(n)).items()))
    zippedList = list(zip(list1[1], list2[1]))
    data  = pd.DataFrame(zippedList, columns = ['Potential' , 'Current'])
    return data


def plot_fig(dict_cycle, n):

    """For basic plotting of the cycle data
  
    Parameters
    __________
    dict: dictionary of dataframes for all the cycles
    n: number of cycles

    Saves the plot in a file called cycle.png 
    """

    for i in range(n):
        print(i+1)
        df = data_frame(dict_cycle, i+1)
        plt.plot(df.Potential, df.Current, label = "Cycle{}".format(i+1))
        
    #print(df.head())
    plt.xlabel('Voltage')
    plt.ylabel('Current')
    plt.legend()
    plt.savefig('cycle.png')
    print('executed')


#split forward and backward sweping data, to make it easier for processing.
def split(vector):
    """
    This function takes an array and splits it into two half.
    """
    split = int(len(vector)/2)
    end = int(len(vector))
    vector1 = np.array(vector)[0:split]
    vector2 = np.array(vector)[split:end]
    return vector1, vector2


def critical_idx(x, y): ## Finds index where data set is no longer linear 

    """
    This function takes x and y values callculate the derrivative of x and y, and calculate moving average of 5 and 15 points.
    Finds intercepts of different moving average curves and return the indexs of the first intercepts.
    """
    k = np.diff(y)/(np.diff(x)) #calculated slops of x and y
    ## Calculate moving average for 5 and 15 points.
    ## This two arbitrary number can be tuned to get better fitting.
    ave5 = []
    ave15 = []
    for i in range(len(k)-10):  # The reason to minus 5 is to prevent j from running out of index.
        a = 0 
        for j in range(0,10):
            a = a + k[i+j]
        ave5.append(round(a/10, 5)) # keeping 9 desimal points for more accuracy
    
    for i in range(len(k)-15): 
        b = 0 
        for j in range(0,15):
            b = b + k[i+j]
        ave15.append(round(b/15, 5))
    ave5i = np.asarray(ave5)
    #print(ave10i)
    ave15i = np.asarray(ave15)
    #print(ave15i)
    ## Find intercepts of different moving average curves
    idx = np.argwhere(np.diff(np.sign(ave15i - ave5i[:len(ave15i)])!= 0)).reshape(-1)+0 #reshape into one row.
    return idx[5]

# This is based on the method 1 where user can't choose the baseline.
# If wanted to add that, choose method2.
def sum_mean(vector):
    """
    This function returns the mean values.
    """
    a = 0
    for i in vector:
        a = a + i
    return [a,a/len(vector)]


def multiplica(vetor_x, vetor_y):
    a = 0
    for x,y in zip(vetor_x, vetor_y):
        a = a + (x * y)
    return a


def linear_coeff(x, y):
    """
    This function returns the inclination coeffecient and y axis interception coeffecient m and b. 
    """
    m = (multiplica(x,y) - sum_mean(x)[0] * sum_mean(y)[1]) / (multiplica(x,x) - sum_mean(x)[0] * sum_mean(x)[1])  
    b = sum_mean(y)[1] - m * sum_mean(x)[1]
    return m, b


def y_fitted_line(m, b, x):
    y_base = []
    for i in x:
        y = m * i + b
        y_base.append(y)
    return y_base


def linear_background(x, y):
    idx = critical_idx(x, y) + 5 #this is also arbitrary number we can play with.
    m, b = linear_coeff(x[(idx - int(0.5 * idx)) : (idx + int(0.5 * idx))], y[(idx - int(0.5 * idx)) : (idx + int(0.5 * idx))])
    y_base = y_fitted_line(m, b, x)
    return y_base

def peak_detection_fxn(data_y):

    """The function takes an input of the column containing the y variables in the dataframe,
    associated with the current. The function calls the split function, which splits the
    column into two arrays, one of the positive and one of the negative values.
    This is because cyclic voltammetry delivers negative peaks, but the peakutils function works
    better with positive peaks. The function also runs on the middle 80% of data to eliminate
    unnecessary noise and messy values associated with pseudo-peaks.The vectors are then imported
    into the peakutils.indexes function to determine the significant peak for each array.
    The values are stored in a list, with the first index corresponding to the top peak and the
    second corresponding to the bottom peak.
    Parameters
    ______________
    y column: must be a column from a pandas dataframe

    Returns
    _____________
    A list with the index of the peaks from the top curve and bottom curve.
    """

    # initialize storage list
    index_list = []

    # split data into above and below the baseline
    col_y1, col_y2 = split(data_y) # removed main. head.

    # detemine length of data and what 10% of the data is
    len_y = len(col_y1)
    ten_percent = int(np.around(0.1*len_y))

    # adjust both input columns to be the middle 80% of data
    # (take of the first and last 10% of data)
    # this avoid detecting peaks from electrolysis
    # (from water splitting and not the molecule itself,
    # which can form random "peaks")
    mod_col_y2 = col_y2[ten_percent:len_y-ten_percent]
    mod_col_y1 = col_y1[ten_percent:len_y-ten_percent]

    # run peakutils package to detect the peaks for both top and bottom
    peak_top = peakutils.indexes(mod_col_y2, thres=0.99, min_dist=20)
    peak_bottom = peakutils.indexes(abs(mod_col_y1), thres=0.99, min_dist=20)

    # detemine length of both halves of data
    len_top = len(peak_top)
    len_bot = len(peak_bottom)

    # append the values to the storage list
    # manipulate values by adding the ten_percent value back
    # (as the indecies have moved)
    # to detect the actual peaks and not the modified values
    index_list.append(peak_top[int(len_top/2)]+ten_percent)
    index_list.append(peak_bottom[int(len_bot/2)]+ten_percent)

    # return storage list
    # first value is the top, second value is the bottom
    return index_list


def peak_values(DataFrame_x, DataFrame_y):

    """Outputs x (potentials) and y (currents) values from data indices
        given by peak_detection function.

       ----------
       Parameters
       ----------
       DataFrame_x : should be in the form of a pandas DataFrame column.
         For example, df['potentials'] could be input as the column of x
         data.

        DataFrame_y : should be in the form of a pandas DataFrame column.
          For example, df['currents'] could be input as the column of y
          data.

       Returns
       -------
       Result : numpy array of coordinates at peaks in the following order:
         potential of peak on top curve, current of peak on top curve,
         potential of peak on bottom curve, current of peak on bottom curve"""
    index = peak_detection_fxn(DataFrame_y)
    potential1, potential2 = split(DataFrame_x)
    current1, current2 = split(DataFrame_y)
    Peak_values = []
    Peak_values.append(potential2[(index[0])])  # TOPX (bottom part of curve is
    # the first part of DataFrame)
    Peak_values.append(current2[(index[0])])  # TOPY
    Peak_values.append(potential1[(index[1])])  # BOTTOMX
    Peak_values.append(current1[(index[1])])  # BOTTOMY
    Peak_array = np.array(Peak_values)
    return Peak_array


def del_potential(DataFrame_x, DataFrame_y):
    """Outputs the difference in potentials between anoidc and
       cathodic peaks in cyclic voltammetry data.

       Parameters
       ----------
       DataFrame_x : should be in the form of a pandas DataFrame column.
         For example, df['potentials'] could be input as the column of x
         data.

        DataFrame_y : should be in the form of a pandas DataFrame column.
          For example, df['currents'] could be input as the column of y
          data.

        Returns
        -------
        Results: difference in peak potentials in the form of a numpy array."""
    del_potentials = (peak_values(DataFrame_x, DataFrame_y)[0] -
                      peak_values(DataFrame_x, DataFrame_y)[2])
    return del_potentials


def half_wave_potential(DataFrame_x, DataFrame_y):
    """Outputs the half wave potential(redox potential) from cyclic
       voltammetry data.

       Parameters
       ----------
       DataFrame_x : should be in the form of a pandas DataFrame column.
         For example, df['potentials'] could be input as the column of x
         data.

        DataFrame_y : should be in the form of a pandas DataFrame column.
          For example, df['currents'] could be input as the column of y
          data.

       Returns
       -------
       Results : the half wave potential in the form of a
         floating point number."""
    half_wave_potential = (del_potential(DataFrame_x, DataFrame_y))/2
    return half_wave_potential


def peak_heights(DataFrame_x, DataFrame_y):

    """Outputs heights of minimum peak and maximum
         peak from cyclic voltammetry data.

       Parameters
       ----------
       DataFrame_x : should be in the form of a pandas DataFrame column.
         For example, df['potentials'] could be input as the column of x
         data.

        DataFrame_y : should be in the form of a pandas DataFrame column.
          For example, df['currents'] could be input as the column of y
          data.

        Returns
        -------
        Results: height of maximum peak, height of minimum peak
          in that order in the form of a list."""
    current_max = peak_values(DataFrame_x, DataFrame_y)[1]
    current_min = peak_values(DataFrame_x, DataFrame_y)[3]
    x1, x2 = split(DataFrame_x)
    y1, y2 = split(DataFrame_y)
    line_at_min = linear_background(x1, y1)[peak_detection_fxn(DataFrame_y)[1]]
    line_at_max = linear_background(x2, y2)[peak_detection_fxn(DataFrame_y)[0]]
    height_of_max = current_max - line_at_max
    height_of_min = abs(current_min - line_at_min)
    return [height_of_max, height_of_min]


def peak_ratio(DataFrame_x, DataFrame_y):
    """Outputs the peak ratios from cyclic voltammetry data.

       Parameters
       ----------
       DataFrame_x : should be in the form of a pandas DataFrame column.
         For example, df['potentials'] could be input as the column of x
         data.

        DataFrame_y : should be in the form of a pandas DataFrame column.
          For example, df['currents'] could be input as the column of y
          data.

       Returns
       -------
       Result : returns a floating point number, the peak ratio."""
    ratio = (peak_heights(DataFrame_x, DataFrame_y)[0] /
             peak_heights(DataFrame_x, DataFrame_y)[1])
    return ratio


1		# This is a tool to automate cyclic voltametry analysis.
2		# Current Version = 1
3
4		import pandas as pd
5		import numpy as np
6		import csv
7		import matplotlib.pyplot as plt
8		import warnings
9		import matplotlib.cbook
10		import peakutils
11		import copy
12		from matplotlib import rcParams
13
14
15	View Code Duplication	def read_cycle(data):
		0 ignored issues – show Duplication introduced 2019-03-18 22:56 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
16		"""This function reads a segment of datafile (corresponding a cycle)
17		and generates a dataframe with columns 'Potential' and 'Current'
18
19		Parameters
20		__________
21		data: segment of data file
22
23		Returns
24		_______
25		A dataframe with potential and current columns
26		"""
27
28		current = []
29		potential = []
30		for i in data[3:]:
31		current.append(float(i.split("\t")[4]))
32		potential.append(float(i.split("\t")[3]))
33		zippedList = list(zip(potential, current))
34		df = pd.DataFrame(zippedList, columns = ['Potential' , 'Current'])
35		return df
36
37
38	View Code Duplication	def read_file_dash(lines):
		0 ignored issues – show Duplication introduced 2019-03-18 22:56 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
39		"""This function is exactly similar to read_file, but it is for dash
40
41		Parameters
42		__________
43		file: lines from dash input file
44
45		Returns:
46		________
47		dict_of_df: dictionary of dataframes with keys = cycle numbers and
48		values = dataframes for each cycle
49		n_cycle: number of cycles in the raw file
50		"""
51		dict_of_df = {}
52		h = 0
53		l = 0
54		n_cycle = 0
55		number = 0
56		#a = []
57		#with open(file, 'rt') as f:
58		# print(file + ' Opened')
59		for line in lines:
60		record = 0
61		if not (h and l):
62		if line.startswith('SCANRATE'):
63		scan_rate = float(line.split()[2])
64		h = 1
65		if line.startswith('STEPSIZE'):
66		step_size = float(line.split()[2])
67		l = 1
68		if line.startswith('CURVE'):
69		n_cycle += 1
70		if n_cycle > 1:
71		number = n_cycle - 1
72		df = read_cycle(a)
73		key_name = 'cycle_' + str(number)
74		#key_name = number
75		dict_of_df[key_name] = copy.deepcopy(df)
76		a = []
77		if n_cycle:
78		a.append(line)
79		return dict_of_df, number
80
81
82	View Code Duplication	def read_file(file):
		0 ignored issues – show Duplication introduced 2019-03-18 22:56 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
83		"""This function reads the raw data file, gets the scanrate and stepsize
84		and then reads the lines according to cycle number. Once it reads the data
85		for one cycle, it calls read_cycle function to generate a dataframe. It
86		does the same thing for all the cycles and finally returns a dictionary,
87		the keys of which are the cycle numbers and the values are the
88		corresponding dataframes.
89
90		Parameters
91		__________
92		file: raw data file
93
94		Returns:
95		________
96		dict_of_df: dictionary of dataframes with keys = cycle numbers and
97		values = dataframes for each cycle
98		n_cycle: number of cycles in the raw file
99		"""
100		dict_of_df = {}
101		h = 0
102		l = 0
103		n_cycle = 0
104		#a = []
105		with open(file, 'rt') as f:
106		print(file + ' Opened')
107		for line in f:
108		record = 0
109		if not (h and l):
110		if line.startswith('SCANRATE'):
111		scan_rate = float(line.split()[2])
112		h = 1
113		if line.startswith('STEPSIZE'):
114		step_size = float(line.split()[2])
115		l = 1
116		if line.startswith('CURVE'):
117		n_cycle += 1
118		if n_cycle > 1:
119		number = n_cycle - 1
120		df = read_cycle(a)
121		key_name = 'cycle_' + str(number)
122		#key_name = number
123		dict_of_df[key_name] = copy.deepcopy(df)
124		a = []
125		if n_cycle:
126		a.append(line)
127		return dict_of_df, number
128
129
130		#df = pd.DataFrame(list(dict1['df_1'].items()))
131		#list1, list2 = list(dict1['df_1'].items())
132		#list1, list2 = list(dict1.get('df_'+str(1)))
133
134	View Code Duplication	def data_frame(dict_cycle, n):
		0 ignored issues – show Duplication introduced 2019-03-18 22:56 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
135		"""Reads the dictionary of dataframes and returns dataframes for each cycle
136
137		Parameters
138		__________
139		dict_cycle: Dictionary of dataframes
140		n: cycle number
141
142		Returns:
143		_______
144		Dataframe correcponding to the cycle number
145		"""
146		list1, list2 = (list(dict_cycle.get('cycle_'+str(n)).items()))
147		zippedList = list(zip(list1[1], list2[1]))
148		data = pd.DataFrame(zippedList, columns = ['Potential' , 'Current'])
149		return data
150
151
152	View Code Duplication	def plot_fig(dict_cycle, n):
		0 ignored issues – show Duplication introduced 2019-03-18 22:56 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
153		"""For basic plotting of the cycle data
154
155		Parameters
156		__________
157		dict: dictionary of dataframes for all the cycles
158		n: number of cycles
159
160		Saves the plot in a file called cycle.png
161		"""
162
163		for i in range(n):
164		print(i+1)
165		df = data_frame(dict_cycle, i+1)
166		plt.plot(df.Potential, df.Current, label = "Cycle{}".format(i+1))
167
168		#print(df.head())
169		plt.xlabel('Voltage')
170		plt.ylabel('Current')
171		plt.legend()
172		plt.savefig('cycle.png')
173		print('executed')
174
175
176		#split forward and backward sweping data, to make it easier for processing.
177		def split(vector):
178		"""
179		This function takes an array and splits it into two half.
180		"""
181		split = int(len(vector)/2)
182		end = int(len(vector))
183		vector1 = np.array(vector)[0:split]
184		vector2 = np.array(vector)[split:end]
185		return vector1, vector2
186
187
188	View Code Duplication	def critical_idx(x, y): ## Finds index where data set is no longer linear
		0 ignored issues – show Duplication introduced 2019-03-18 22:56 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
189		"""
190		This function takes x and y values callculate the derrivative of x and y, and calculate moving average of 5 and 15 points.
191		Finds intercepts of different moving average curves and return the indexs of the first intercepts.
192		"""
193		k = np.diff(y)/(np.diff(x)) #calculated slops of x and y
194		## Calculate moving average for 5 and 15 points.
195		## This two arbitrary number can be tuned to get better fitting.
196		ave5 = []
197		ave15 = []
198		for i in range(len(k)-10): # The reason to minus 5 is to prevent j from running out of index.
199		a = 0
200		for j in range(0,10):
201		a = a + k[i+j]
202		ave5.append(round(a/10, 5)) # keeping 9 desimal points for more accuracy
203
204		for i in range(len(k)-15):
205		b = 0
206		for j in range(0,15):
207		b = b + k[i+j]
208		ave15.append(round(b/15, 5))
209		ave5i = np.asarray(ave5)
210		#print(ave10i)
211		ave15i = np.asarray(ave15)
212		#print(ave15i)
213		## Find intercepts of different moving average curves
214		idx = np.argwhere(np.diff(np.sign(ave15i - ave5i[:len(ave15i)])!= 0)).reshape(-1)+0 #reshape into one row.
215		return idx[5]
216
217		# This is based on the method 1 where user can't choose the baseline.
218		# If wanted to add that, choose method2.
219		def sum_mean(vector):
220		"""
221		This function returns the mean values.
222		"""
223		a = 0
224		for i in vector:
225		a = a + i
226		return [a,a/len(vector)]
227
228
229		def multiplica(vetor_x, vetor_y):
230		a = 0
231		for x,y in zip(vetor_x, vetor_y):
232		a = a + (x * y)
233		return a
234
235
236		def linear_coeff(x, y):
237		"""
238		This function returns the inclination coeffecient and y axis interception coeffecient m and b.
239		"""
240		m = (multiplica(x,y) - sum_mean(x)[0] * sum_mean(y)[1]) / (multiplica(x,x) - sum_mean(x)[0] * sum_mean(x)[1])
241		b = sum_mean(y)[1] - m * sum_mean(x)[1]
242		return m, b
243
244
245		def y_fitted_line(m, b, x):
246		y_base = []
247		for i in x:
248		y = m * i + b
249		y_base.append(y)
250		return y_base
251
252
253		def linear_background(x, y):
254		idx = critical_idx(x, y) + 5 #this is also arbitrary number we can play with.
255		m, b = linear_coeff(x[(idx - int(0.5 * idx)) : (idx + int(0.5 * idx))], y[(idx - int(0.5 * idx)) : (idx + int(0.5 * idx))])
256		y_base = y_fitted_line(m, b, x)
257		return y_base
258
259	View Code Duplication	def peak_detection_fxn(data_y):
		0 ignored issues – show Duplication introduced 2019-03-18 22:56 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
260		"""The function takes an input of the column containing the y variables in the dataframe,
261		associated with the current. The function calls the split function, which splits the
262		column into two arrays, one of the positive and one of the negative values.
263		This is because cyclic voltammetry delivers negative peaks, but the peakutils function works
264		better with positive peaks. The function also runs on the middle 80% of data to eliminate
265		unnecessary noise and messy values associated with pseudo-peaks.The vectors are then imported
266		into the peakutils.indexes function to determine the significant peak for each array.
267		The values are stored in a list, with the first index corresponding to the top peak and the
268		second corresponding to the bottom peak.
269		Parameters
270		______________
271		y column: must be a column from a pandas dataframe
272
273		Returns
274		_____________
275		A list with the index of the peaks from the top curve and bottom curve.
276		"""
277
278		# initialize storage list
279		index_list = []
280
281		# split data into above and below the baseline
282		col_y1, col_y2 = split(data_y) # removed main. head.
283
284		# detemine length of data and what 10% of the data is
285		len_y = len(col_y1)
286		ten_percent = int(np.around(0.1*len_y))
287
288		# adjust both input columns to be the middle 80% of data
289		# (take of the first and last 10% of data)
290		# this avoid detecting peaks from electrolysis
291		# (from water splitting and not the molecule itself,
292		# which can form random "peaks")
293		mod_col_y2 = col_y2[ten_percent:len_y-ten_percent]
294		mod_col_y1 = col_y1[ten_percent:len_y-ten_percent]
295
296		# run peakutils package to detect the peaks for both top and bottom
297		peak_top = peakutils.indexes(mod_col_y2, thres=0.99, min_dist=20)
298		peak_bottom = peakutils.indexes(abs(mod_col_y1), thres=0.99, min_dist=20)
299
300		# detemine length of both halves of data
301		len_top = len(peak_top)
302		len_bot = len(peak_bottom)
303
304		# append the values to the storage list
305		# manipulate values by adding the ten_percent value back
306		# (as the indecies have moved)
307		# to detect the actual peaks and not the modified values
308		index_list.append(peak_top[int(len_top/2)]+ten_percent)
309		index_list.append(peak_bottom[int(len_bot/2)]+ten_percent)
310
311		# return storage list
312		# first value is the top, second value is the bottom
313		return index_list
314
315
316	View Code Duplication	def peak_values(DataFrame_x, DataFrame_y):
		0 ignored issues – show Duplication introduced 2019-03-18 22:56 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
317		"""Outputs x (potentials) and y (currents) values from data indices
318		given by peak_detection function.
319
320		----------
321		Parameters
322		----------
323		DataFrame_x : should be in the form of a pandas DataFrame column.
324		For example, df['potentials'] could be input as the column of x
325		data.
326
327		DataFrame_y : should be in the form of a pandas DataFrame column.
328		For example, df['currents'] could be input as the column of y
329		data.
330
331		Returns
332		-------
333		Result : numpy array of coordinates at peaks in the following order:
334		potential of peak on top curve, current of peak on top curve,
335		potential of peak on bottom curve, current of peak on bottom curve"""
336		index = peak_detection_fxn(DataFrame_y)
337		potential1, potential2 = split(DataFrame_x)
338		current1, current2 = split(DataFrame_y)
339		Peak_values = []
340		Peak_values.append(potential2[(index[0])]) # TOPX (bottom part of curve is
341		# the first part of DataFrame)
342		Peak_values.append(current2[(index[0])]) # TOPY
343		Peak_values.append(potential1[(index[1])]) # BOTTOMX
344		Peak_values.append(current1[(index[1])]) # BOTTOMY
345		Peak_array = np.array(Peak_values)
346		return Peak_array
347
348
349		def del_potential(DataFrame_x, DataFrame_y):
350		"""Outputs the difference in potentials between anoidc and
351		cathodic peaks in cyclic voltammetry data.
352
353		Parameters
354		----------
355		DataFrame_x : should be in the form of a pandas DataFrame column.
356		For example, df['potentials'] could be input as the column of x
357		data.
358
359		DataFrame_y : should be in the form of a pandas DataFrame column.
360		For example, df['currents'] could be input as the column of y
361		data.
362
363		Returns
364		-------
365		Results: difference in peak potentials in the form of a numpy array."""
366		del_potentials = (peak_values(DataFrame_x, DataFrame_y)[0] -
367		peak_values(DataFrame_x, DataFrame_y)[2])
368		return del_potentials
369
370
371		def half_wave_potential(DataFrame_x, DataFrame_y):
372		"""Outputs the half wave potential(redox potential) from cyclic
373		voltammetry data.
374
375		Parameters
376		----------
377		DataFrame_x : should be in the form of a pandas DataFrame column.
378		For example, df['potentials'] could be input as the column of x
379		data.
380
381		DataFrame_y : should be in the form of a pandas DataFrame column.
382		For example, df['currents'] could be input as the column of y
383		data.
384
385		Returns
386		-------
387		Results : the half wave potential in the form of a
388		floating point number."""
389		half_wave_potential = (del_potential(DataFrame_x, DataFrame_y))/2
390		return half_wave_potential
391
392
393	View Code Duplication	def peak_heights(DataFrame_x, DataFrame_y):
		0 ignored issues – show Duplication introduced 2019-03-18 22:56 UTC by Report Bug Copy Issue Report This code seems to be duplicated in your project. Loading history...
394		"""Outputs heights of minimum peak and maximum
395		peak from cyclic voltammetry data.
396
397		Parameters
398		----------
399		DataFrame_x : should be in the form of a pandas DataFrame column.
400		For example, df['potentials'] could be input as the column of x
401		data.
402
403		DataFrame_y : should be in the form of a pandas DataFrame column.
404		For example, df['currents'] could be input as the column of y
405		data.
406
407		Returns
408		-------
409		Results: height of maximum peak, height of minimum peak
410		in that order in the form of a list."""
411		current_max = peak_values(DataFrame_x, DataFrame_y)[1]
412		current_min = peak_values(DataFrame_x, DataFrame_y)[3]
413		x1, x2 = split(DataFrame_x)
414		y1, y2 = split(DataFrame_y)
415		line_at_min = linear_background(x1, y1)[peak_detection_fxn(DataFrame_y)[1]]
416		line_at_max = linear_background(x2, y2)[peak_detection_fxn(DataFrame_y)[0]]
417		height_of_max = current_max - line_at_max
418		height_of_min = abs(current_min - line_at_min)
419		return [height_of_max, height_of_min]
420
421
422		def peak_ratio(DataFrame_x, DataFrame_y):
423		"""Outputs the peak ratios from cyclic voltammetry data.
424
425		Parameters
426		----------
427		DataFrame_x : should be in the form of a pandas DataFrame column.
428		For example, df['potentials'] could be input as the column of x
429		data.
430
431		DataFrame_y : should be in the form of a pandas DataFrame column.
432		For example, df['currents'] could be input as the column of y
433		data.
434
435		Returns
436		-------
437		Result : returns a floating point number, the peak ratio."""
438		ratio = (peak_heights(DataFrame_x, DataFrame_y)[0] /
439		peak_heights(DataFrame_x, DataFrame_y)[1])
440		return ratio
441

sabiharustam / voltcycle

GitHub Access Token became invalid

Push — master ( 0c3829...de7c60 )

dash_resumable_upload.read_file_dash() C

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like