main change

data_exploration.py

 import numpy as np
 import matplotlib.pyplot as plt
 import matplotlib
+import pandas as pd
 
 matplotlib.use('agg')
 length = 30
@@ -284,3 +285,13 @@ def RT_distrib(Y, f_name):
 # RT_distrib(Y_validation,'fig/histo_RT_validation.png' )
 #
 #
+#ISA DATA
+
+df = pd.read_pickle('database/data_ISA_aligned_prosit.pkl')
+seq = df['Sequence'].unique()
+# rt = df['Retention time']
+df_mean = df.groupby(['Sequence'])['Retention time'].mean()
+# feq_aa(seq, plot=False, save=True, f_name='fig/histo_aa_ISA_unique.png')
+# dist_long(seq, plot=False, save=True, f_name='fig/histo_length_ISA_unique.png')
+
+RT_distrib(df_mean, 'fig/histo_RT_ISA_unique.png')

data_viz.py

@@ -254,7 +254,7 @@ def add_length(dataframe):
     dataframe['length']=dataframe['seq'].map(fonc)
 
 
-df = pd.read_csv('output/out_common_ISA_ISA_eval_2.csv')
+# df = pd.read_csv('output/out_common_ISA_ISA_eval_2.csv')
 # add_length(df)
 # df['abs_error'] =  np.abs(df['rt pred']-df['true rt'])
 # histo_abs_error(df, display=False, save=True, path='fig/custom model res/histo_ISA_ISA_eval.png')
@@ -275,11 +275,11 @@ df = pd.read_csv('output/out_common_ISA_ISA_eval_2.csv')
 # scatter_rt(df, display=False, save=True, path='fig/custom model res/RT_pred_prosit_ISA_eval.png', color=True)
 # histo_length_by_error(df, bins=10, display=False, save=True, path='fig/custom model res/histo_length_prosit_ISA_eval.png')
 
-# df = pd.read_csv('output/out_common_ISA_ISA_eval_3.csv')
+# df = pd.read_csv('output/out_common_ISA_prosit_eval.csv')
 # add_length(df)
 # df['abs_error'] =  np.abs(df['rt pred']-df['true rt'])
-# histo_abs_error(df, display=False, save=True, path='fig/custom model res/histo_ISA_ISA_eval_3.png')
-# scatter_rt(df, display=False, save=True, path='fig/custom model res/RT_pred_ISA_ISA_eval_3_file.png', color=True, col = 'file')
-# histo_length_by_error(df, bins=10, display=False, save=True, path='fig/custom model res/histo_length_ISA_ISA_eval_3.png')
-
+# histo_abs_error(df, display=False, save=True, path='fig/custom model res/histo_ISA_prosit_eval.png')
+# scatter_rt(df, display=False, save=True, path='fig/custom model res/RT_pred_ISA_prosit_eval.png', color=True, col = 'seq')
+# histo_length_by_error(df, bins=10, display=False, save=True, path='fig/custom model res/histo_length_ISA_prosit_eval.png')
+#