datasets

data_viz.py

@@ -275,15 +275,12 @@ 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_augmented_10_eval.csv')
 add_length(df)
-df['rt pred'] =  0
-for seq, gr in df.groupby('seq') :
-    df.loc[df['seq']==seq,'rt pred']=gr['true rt'].mean()
-# 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')
-scatter_rt(df, display=False, save=True, path='fig/custom model res/RT_pred_ISA_ISA_best_possible.png', color=True)
-# histo_length_by_error(df, bins=10, display=False, save=True, path='fig/custom model res/histo_length_ISA_ISA_eval.png')
+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_SA_augmented_10_eval.png')
+scatter_rt(df, display=False, save=True, path='fig/custom model res/RT_pred_SA_augmented_10_eval.png', color=True)
+histo_length_by_error(df, bins=10, display=False, save=True, path='fig/custom model res/histo_length_SA_augmented_10_eval.png')
 #
 # df = pd.read_csv('output/out_common_ISA_augmented_3_eval.csv')
 # add_length(df)
@@ -308,10 +305,10 @@ scatter_rt(df, display=False, save=True, path='fig/custom model res/RT_pred_ISA_
 
 ## Compare error variation between run
 ## Prosit column changes affect some peptides more than others (but consistently)
-df_1 = pd.read_csv('output/out_common_ISA_prosit_eval.csv')
-df_2 = pd.read_csv('output/out_common_ISA_prosit_eval_2.csv')
-
-df = select_best_data(df_1, df_2, 7)
-df.to_pickle('database/data_prosit_threshold_7.pkl')
+# df_1 = pd.read_csv('output/out_common_ISA_prosit_eval.csv')
+# df_2 = pd.read_csv('output/out_common_ISA_prosit_eval_2.csv')
+#
+# df = select_best_data(df_1, df_2, 7)
+# df.to_pickle('database/data_prosit_threshold_7.pkl')
 # compare_error(df_1,df_2,save=True,path='fig/custom model res/ISA_prosit_error_variation.png')