added example_minimal_case.py to examples

mpecchi · Jun 6, 2024 · 0e3c44c · 0e3c44c
1 parent 6d6d40a
commit 0e3c44c
Show file tree

Hide file tree

Showing 25 changed files with 176 additions and 130 deletions.
diff --git a/example/example_minimal_case.py b/example/example_minimal_case.py
diff --git a/example/data/A_1.txt → examples/data/A_1.txt b/example/data/A_1.txt → examples/data/A_1.txt
diff --git a/example/data/A_2.txt → examples/data/A_2.txt b/example/data/A_2.txt → examples/data/A_2.txt
diff --git a/example/data/Ader_1.txt → examples/data/Ader_1.txt b/example/data/Ader_1.txt → examples/data/Ader_1.txt
diff --git a/example/data/Ader_2.txt → examples/data/Ader_2.txt b/example/data/Ader_2.txt → examples/data/Ader_2.txt
diff --git a/example/data/B_1.txt → examples/data/B_1.txt b/example/data/B_1.txt → examples/data/B_1.txt
diff --git a/example/data/B_2.txt → examples/data/B_2.txt b/example/data/B_2.txt → examples/data/B_2.txt
diff --git a/example/data/calibration.xlsx → examples/data/calibration.xlsx b/example/data/calibration.xlsx → examples/data/calibration.xlsx
diff --git a/...data/classifications_codes_fractions.xlsx → ...data/classifications_codes_fractions.xlsx b/...data/classifications_codes_fractions.xlsx → ...data/classifications_codes_fractions.xlsx
diff --git a/example/data/deriv_calibration.xlsx → examples/data/deriv_calibration.xlsx b/example/data/deriv_calibration.xlsx → examples/data/deriv_calibration.xlsx
diff --git a/example/data/files_info.xlsx → examples/data/files_info.xlsx b/example/data/files_info.xlsx → examples/data/files_info.xlsx
diff --git a/examples/data_minimal_case/S_1.txt b/examples/data_minimal_case/S_1.txt
@@ -0,0 +1,15 @@
+[Header]
+Data File Name	C:\Users\user\Documents\jla278\T1.qgd
+Output Date	3/18/2024
+Output Time	11:00:20 AM
+
+[MC Peak Table]
+# of Peaks	3
+Mass	TIC
+Peak#	Ret.Time	Proc.From	Proc.To	Mass	Area	Height	A/H	Conc.	Mark	Name	Ret. Index	Area%	Height%	SI	CAS #
+1	13.703	13.580	13.900	TIC	20	20	1	0	 V 	Capric Acid		2.59	3.01	97	108-95-2
+2	20.942	20.767	21.020	TIC	200	200	1	0	 V 	Naphthalene		8.11	9.20	98	91-20-3
+3	21.426	21.373	21.500	TIC	2000	2000	1	0	 V 	Dodecane		0.36	0.57	96	112-40-3
+4	22.426	22.373	22.500	TIC	1000	1000	1	0	 V 	NotValidComp		0.36	0.57	96	112-40-3
+5	23.426	22.373	22.500	TIC	1000	100	1	0	 V 	Palmitic Acid		0.36	0.57	96	112-40-3
+6	24.426	22.373	22.500	TIC	1000	200	1	0	 V 	Dichlorobenzene		0.36	0.57	96	112-40-3
diff --git a/examples/data_minimal_case/S_2.txt b/examples/data_minimal_case/S_2.txt
@@ -0,0 +1,13 @@
+[Header]
+Data File Name	C:\Users\user\Documents\jla278\T1.qgd
+Output Date	3/18/2024
+Output Time	11:00:20 AM
+
+[MC Peak Table]
+# of Peaks	3
+Mass	TIC
+Peak#	Ret.Time	Proc.From	Proc.To	Mass	Area	Height	A/H	Conc.	Mark	Name	Ret. Index	Area%	Height%	SI	CAS #
+1	13.703	13.580	13.900	TIC	40	40	1	0	 V 	Capric Acid		2.59	3.01	97	108-95-2
+2	20.942	20.767	21.020	TIC	400	400	1	0	 V 	Naphthalene		8.11	9.20	98	91-20-3
+3	21.426	21.373	21.500	TIC	4000	4000	1	0	 V 	Dodecane		0.36	0.57	96	112-40-3
+4	24.426	26.373	21.500	TIC	1000	1000	1	0	 V 	Almost Oleic Acid		0.36	0.57	96	112-40-3
diff --git a/examples/data_minimal_case/T_1.txt b/examples/data_minimal_case/T_1.txt
@@ -0,0 +1,12 @@
+[Header]
+Data File Name	C:\Users\user\Documents\jla278\T1.qgd
+Output Date	3/18/2024
+Output Time	11:00:20 AM
+
+[MC Peak Table]
+# of Peaks	3
+Mass	TIC
+Peak#	Ret.Time	Proc.From	Proc.To	Mass	Area	Height	A/H	Conc.	Mark	Name	Ret. Index	Area%	Height%	SI	CAS #
+1	13.703	13.580	13.900	TIC	20	20	1	0	 V 	Phenol		2.59	3.01	97	108-95-2
+2	20.942	20.767	21.020	TIC	50	50	1	0	 V 	Naphthalene		8.11	9.20	98	91-20-3
+3	21.426	21.373	21.500	TIC	500	500	1	0	 V 	Dodecane		0.36	0.57	96	112-40-3
diff --git a/examples/data_minimal_case/T_2.txt b/examples/data_minimal_case/T_2.txt
@@ -0,0 +1,12 @@
+[Header]
+Data File Name	C:\Users\user\Documents\jla278\T2.qgd
+Output Date	3/18/2024
+Output Time	11:00:20 AM
+
+[MC Peak Table]
+# of Peaks	3
+Mass	TIC
+Peak#	Ret.Time	Proc.From	Proc.To	Mass	Area	Height	A/H	Conc.	Mark	Name	Ret. Index	Area%	Height%	SI	CAS #
+1	13.703	13.580	13.900	TIC	10	10	1	0	 V 	Phenol		2.59	3.01	97	108-95-2
+2	20.942	20.767	21.020	TIC	100	1000	1	0	 V 	Naphthalene		8.11	9.20	98	91-20-3
+3	21.426	21.373	21.500	TIC	1000	1000	1	0	 V 	Dodecane		0.36	0.57	96	112-40-3
diff --git a/examples/data_minimal_case/T_3.txt b/examples/data_minimal_case/T_3.txt
@@ -0,0 +1,12 @@
+[Header]
+Data File Name	C:\Users\user\Documents\jla278\T3.qgd
+Output Date	3/18/2024
+Output Time	11:00:20 AM
+
+[MC Peak Table]
+# of Peaks	3
+Mass	TIC
+Peak#	Ret.Time	Proc.From	Proc.To	Mass	Area	Height	A/H	Conc.	Mark	Name	Ret. Index	Area%	Height%	SI	CAS #
+1	13.703	13.580	13.900	TIC	10	10	1	0	 V 	Phenol		2.59	3.01	97	108-95-2
+2	20.942	20.767	21.020	TIC	100	1000	1	0	 V 	Naphthalene		8.11	9.20	98	91-20-3
+3	21.426	21.373	21.500	TIC	1000	1000	1	0	 V 	Dodecane		0.36	0.57	96	112-40-3
diff --git a/examples/data_minimal_case/cal_minimal.xlsx b/examples/data_minimal_case/cal_minimal.xlsx
diff --git a/...ties/classifications_codes_fractions.xlsx → ...case/classifications_codes_fractions.xlsx b/...ties/classifications_codes_fractions.xlsx → ...case/classifications_codes_fractions.xlsx
diff --git a/examples/data_minimal_case/compounds_properties.xlsx b/examples/data_minimal_case/compounds_properties.xlsx
diff --git a/examples/data_minimal_case/files_info.xlsx b/examples/data_minimal_case/files_info.xlsx
diff --git a/examples/example_minimal_case.py b/examples/example_minimal_case.py
@@ -0,0 +1,112 @@
+# %% Import necessary libraries
+import pathlib as plib
+from gcms_data_analysis.gcms import Project
+
+folder_path: plib.Path = plib.Path(__file__).parent
+
+folder_path = r"/Users/matteo/Projects/gcms_data_analysis/examples/data_minimal_case"
+
+proj = Project(
+    folder_path=folder_path,
+    auto_save_to_excel=False,
+    compounds_to_rename_in_files={
+        "almost oleic acid": "oleic acid",
+        "dichlorobenzene": "p-dichlorobenzene",
+    },
+)
+
+# %%
+files_info_created = proj.create_files_info(update_saved_files_info=False)
+print(files_info_created.T)
+
+files_info_loaded = proj.load_files_info(update_saved_files_info=False)
+print(files_info_loaded.T)
+# %%
+files = proj.load_all_files()
+print(files["S_1"])
+# %%
+class_code_frac = proj.load_class_code_frac()
+print(class_code_frac)
+# %%
+calibrations = proj.load_calibrations()
+print(calibrations["cal_minimal"])
+# %%
+list_of_all_compounds = proj.create_list_of_all_compounds()
+print(list_of_all_compounds)
+# %%
+compounds_properties_created = proj.create_compounds_properties(
+    update_saved_files_info=True
+)
+compounds_properties_loaded = proj.load_compounds_properties()
+print(compounds_properties_created)
+# %%
+dict_names_to_iupac = proj.create_dict_names_to_iupacs()
+print(dict_names_to_iupac)
+
+# %%
+files_iupac, calibration_iupac = proj.add_iupac_to_files_and_calibrations()
+print(files_iupac["S_1"])
+print(calibration_iupac["cal_minimal"])
+# %%
+tanimoto_similarity_df, mol_weight_diff_df = (
+    proj.create_tanimoto_and_molecular_weight_similarity_dfs()
+)
+print(tanimoto_similarity_df)
+print(mol_weight_diff_df)
+# %%
+semi_calibratoin_dict = proj.create_semi_calibration_dict()
+print(semi_calibratoin_dict)
+# %%
+file1 = proj.apply_calib_to_single_file("S_1")
+file2 = proj.apply_calib_to_single_file("S_2")
+print(file1)
+# %%
+files_calibrated = proj.apply_calibration_to_files()
+print(files_calibrated["S_1"])
+# %%
+file_info_with_stats = proj.add_stats_to_files_info()
+print(file_info_with_stats)
+# %%
+samples_info_ave, samples_info_std = proj.create_samples_info()
+print(samples_info_ave.T)
+print(samples_info_std.T)
+# %%
+sample1_ave, sample1_std = proj.create_single_sample_from_files(
+    files_in_sample=[file1, file2], samplename="S"
+)
+# %%
+samples, samples_std = proj.create_samples_from_files()
+# %%
+reph = proj.create_files_param_report(param="height")
+print(reph)
+
+repc = proj.create_files_param_report(param="conc_vial_mg_L")
+print(repc)
+# %%
+repsh, repsh_d = proj.create_samples_param_report(param="height")
+print(repsh)
+repsc, repsc_d = proj.create_samples_param_report(param="conc_vial_mg_L")
+print(repsc)
+# %%
+aggh = proj.create_files_param_aggrrep(param="height")
+print(aggh)
+# %%
+aggc = proj.create_files_param_aggrrep(param="conc_vial_mg_L")
+
+print(aggc)
+# %%
+aggsh, aggsh_d = proj.create_samples_param_aggrrep(param="height")
+print(aggsh)
+print(aggsh_d)
+# %%
+aggsc, aggsc_d = proj.create_samples_param_aggrrep(param="conc_vial_mg_L")
+
+print(aggsc)
+print(aggsc_d)
+# %%
+proj.save_files_samples_reports()
+# %%
+
+proj.plot_report()
+
+# %%
diff --git a/...perties/checked_compounds_properties.xlsx → ...perties/checked_compounds_properties.xlsx b/...perties/checked_compounds_properties.xlsx → ...perties/checked_compounds_properties.xlsx
diff --git a/examples/name_to_properties/data_name_to_properties/classifications_codes_fractions.xlsx b/examples/name_to_properties/data_name_to_properties/classifications_codes_fractions.xlsx
diff --git a/..._properties/example_name_to_properties.py → ..._properties/example_name_to_properties.py b/..._properties/example_name_to_properties.py → ..._properties/example_name_to_properties.py
diff --git a/tests/test_project_class.py b/tests/test_project_class.py
@@ -5,7 +5,6 @@
 import pandas as pd
 from pandas.testing import assert_frame_equal
 import numpy as np
-import shutil
 
 folder_path: plib.Path = plib.Path(__file__).parent