def CustomPivot():
root = Tk()
root.withdraw()
a = filedialog.askopenfilename(initialdir = "D:\PhytonSCripts\MQOutput" \
,title = "Choose a MQ DP_peptides.deppep file to plot",\
filetypes = (("deppep files","*.deppep"),("all files","*.*")))
a = pd.read_table(a,low_memory=False)
a = a.drop(0).reset_index(drop = True)
b = filedialog.askopenfilename(initialdir = "D:\PhytonSCripts\MQOutput" \
,title = "Choose a MQ DP_peptides.deppep file to plot",\
filetypes = (("deppep files","*.deppep"),("all files","*.*")))
b = pd.read_table(b,low_memory=False)
b = b.drop(0).reset_index(drop = True)
a['Intensity'] = a['Intensity'].astype(float)
b['Intensity'] = b['Intensity'].astype(float)
raw_tablea = pd.pivot_table(a, values = 'Intensity',\
index = ['DP Cluster Index','DP AA','DP Base Sequence'], columns = 'Raw file')
raw_tableb = pd.pivot_table(b, values = 'Intensity',\
index = ['DP Cluster Index','DP AA','DP Base Sequence'], columns = 'Raw file')
raw_tablea = raw_tablea.reset_index()
raw_tableb = raw_tableb.reset_index()
# magic
extractRows(raw_tablea)
return raw_tablea,raw_tableb
def CustomPivot():
start_time = time.time()
root = Tk()
root.withdraw()
a = filedialog.askopenfilename(initialdir = "D:\Thomas\PhytonSCripts\MQOutput" \
,title = "Choose a MQ DP_peptides.deppep file to plot",\
filetypes = (("deppep files","*.deppep"),("all files","*.*")))
a = pd.read_table(a, low_memory=False)
a = a.drop(0).reset_index(drop=True)
a['Intensity'] = a['Intensity'].astype(float)
table = pd.pivot_table(a, values = 'Intensity',\
index = ['DP Cluster Index','DP AA','DP Base Sequence','DP Probabilities'], columns = 'Raw file')
table = table.reset_index()
# magic
table = extractRowsandPivot(table)
table = table.sort_values(by=['DP Cluster Index'])
table = table.reset_index(drop=True)
print("---Runtime = %s minutes ---" % (time.time() - start_time))
return table
def janspivot(a,reg):
if reg:
table = pd.pivot_table(a, values = 'Intensity',\
index = ['DP Cluster Index','DP AA','DP Base Sequence','DP Probabilities',\
'DP Probabilities after Regression'], columns = 'Raw file')
table = table.reset_index()
grouped = table.groupby(['DP Cluster Index', 'DP Base Sequence'])
probs = grouped['DP Probabilities'].apply(lambda df: ';'.join(df))
means = grouped.apply(lambda df: df[table.columns[4:]].mean())
probsreg = grouped['DP Probabilities after Regression'].apply(lambda df: ';'.join(df))
pivot = pd.concat([probs,probsreg,means], axis=1)
pivot = pivot.reset_index()
else:
table = pd.pivot_table(a, values = 'Intensity',\
index = ['DP Cluster Index','DP AA','DP Base Sequence','DP Probabilities'], columns = 'Raw file')
table = table.reset_index()
grouped = table.groupby(['DP Cluster Index', 'DP Base Sequence'])
probs = grouped['DP Probabilities'].apply(lambda df: ';'.join(df))
means = grouped.apply(lambda df: df[table.columns[4:]].mean())
pivot = pd.concat([probs,means], axis=1)
pivot = pivot.reset_index()
return pivot
# -*- coding: utf-8 -*-
"""
Created on Fri Apr 6 13:56:14 2018
@author: heinzinger
"""
import time as time
from perseuspy import pd
from tkinter import Tk
from tkinter import filedialog
if __name__ == "__main__":
start_time = time.time()
root = Tk()
root.withdraw()
a = filedialog.askopenfilename(initialdir = "D:\PhytonSCripts\MQOutput" \
,title = "Choose a MQ DP_peptides.deppep file to plot",\
filetypes = (("deppep files","*.deppep"),("all files","*.*")))
a = pd.read_table(a, low_memory=False)
a = a.drop(0).reset_index(drop=True)
a['Intensity'] = a['Intensity'].astype(float)
table = pd.pivot_table(a, values = 'Intensity',\
index = ['DP Cluster Index','DP Base Sequence'], columns = 'Raw file')
table = table.reset_index()
print("---Runtime = %s seconds ---" % (time.time() - start_time))
def testMQ():
root = Tk()
root.withdraw()
a = filedialog.askopenfilename(initialdir = "D:\Thomas\PhytonSCripts\MQOutput" \
,title = "Choose a MQ nomatch.deppep file to plot",\
filetypes = (("deppep files","*.deppep"),("all files","*.*")))
a = pd.read_table(a, low_memory=False)
a = a.drop(0).reset_index(drop=True)
b = filedialog.askopenfilename(initialdir = "D:\Thomas\PhytonSCripts\MQOutput" \
,title = "Choose a MQ matching.deppep file to plot",\
filetypes = (("deppep files","*.deppep"),("all files","*.*")))
b = pd.read_table(b, low_memory=False)
b = b.drop(0).reset_index(drop=True)
arg = a[[
'Raw file', 'DP Base Raw File', 'DP Proteins', 'DP Base Sequence'
]]
argb = b[[
'Raw file', 'DP Base Raw File', 'DP Proteins', 'DP Base Sequence'
]]
uniq = arg['DP Base Sequence'].unique()
uniqb = argb['DP Base Sequence'].unique()
out = uniq[np.in1d(uniq, uniqb)]
df = pd.DataFrame({'Raw Files': arg['Raw file'].unique()})
df['counta'] = 0
df['countb'] = 0
count = 0
countb = 0
for x in range(len(out)):
coin = arg[arg['DP Base Sequence'] == out[x]]
coinb = argb[argb['DP Base Sequence'] == out[x]]
coincount = np.in1d(coin['Raw file'].unique(),
coinb['Raw file'].unique())
coinbcount = np.in1d(coinb['Raw file'].unique(),
coin['Raw file'].unique())
count = count + coincount[coincount == False].size
countb = countb + coinbcount[coinbcount == False].size
for y in (coin['Raw file'].unique()[coincount == False]):
df['counta'][df['Raw Files'] ==
y] = df['counta'][df['Raw Files'] == y] + 1
for z in (coinb['Raw file'].unique()[coinbcount == False]):
df['countb'][df['Raw Files'] ==
z] = df['countb'][df['Raw Files'] == z] + 1
df.plot.bar()
print('Amount of peptide sequences found in the Raw Files of file 1 but not'\
' found in the Raw Files of file 2 is ',count, '. For file 2: ', countb)
print('!!!Both peptide sequences need to be present in both files!!!')
print('Amount of dp. Peptides in file 1: ', len(a), ' in file 2: ', len(b))
values = pd.DataFrame(a['Raw file'].value_counts())
values['Raw'] = b['Raw file'].value_counts().values
values.columns = ['No match', 'Matching']
values = values.sort_index()
values.plot.bar()
a['Intensity'] = a['Intensity'].astype(float)
b['Intensity'] = b['Intensity'].astype(float)
raw_tablea = pd.pivot_table(a, values = 'Intensity',\
index = ['DP Cluster Index','DP AA','DP Base Sequence','DP Probabilities'], columns = 'Raw file')
raw_tableb = pd.pivot_table(b, values = 'Intensity',\
index = ['DP Cluster Index','DP AA','DP Base Sequence','DP Probabilities'], columns = 'Raw file')
raw_tablea = raw_tablea.reset_index()
raw_tableb = raw_tableb.reset_index()
return raw_tablea, raw_tableb
def MSFrgPivot(a):
a['Raw file'] = a['Spectrum'].apply(lambda df: df.split('.')[0])
a[a['Observed Modifications']!='Unknown']
table = pd.pivot_table(a, values = 'Calculated M/Z',index = ['Peptide','Observed Modifications'], columns = 'Raw file')
pivot = table.reset_index()
return pivot