packages imports

src/common.py

@@ -16,6 +16,11 @@ css_file = Path("style/style_model.css")
 pages_folder = Path("pages/")
 image_path = Path('./images/img-sky.jpg')
 
+import os
+from shutil import rmtree
+from pandas import DataFrame
+from PIL import Image
+import plotly.express as px
 
 
 from utils.data_parsing import JcampParser, CsvParser

src/pages/1-samples_selection.py

@@ -127,6 +127,7 @@ else:
                     @st.cache_data
                     def read_dx(tmp_path):
                         M = JcampParser(path = tmp_path)
+                        M.parse()
                         return M.chem_data, M.specs_df_, M.md_df_, M.md_df_st_
                     _, spectra, meta_data, md_df_st_ = read_dx(tmp_path = tmp_path)
 

src/pages/3-prediction.py

-from packages import *
+from common import *
 st.set_page_config(page_title="NIRS Utils", page_icon=":goat:", layout="wide")
-from utils.data_handling import *
+
+
+
+
+
+# layout
+UiComponents(pagespath = pages_folder, csspath= css_file,imgpath=image_path ,
+             header=True, sidebar= True, bgimg=False, colborders=True)
 # HTML pour le bandeau "CEFE - CNRS"
 # bandeau_html = """
 # <div style="width: 100%; background-color: #4682B4; padding: 10px; margin-bottom: 10px;">

src/style/layout.py

-# from packages import *
-import streamlit as st
+
+
 
 def UiComponents(pagespath, csspath, imgpath, header = True, sidebar = True, bgimg = True, colborders = True):
     import streamlit as st

src/utils/clustering.py

-from packages import *
-
-
 
 #~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~  kmeans ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 
 class Sk_Kmeans:

src/utils/data_handling.py

-from packages import *
 from utils.eval_metrics import metrics
 
 ## try to automatically detect the field separator within the CSV

src/utils/data_parsing.py

-from packages import *
 import jcamp as jc
 
 class JcampParser:
-    import jcamp
     '''This module is designed to help retrieve spectral data as well as metadata of smaples  from jcamp file'''
     def __init__(self, path):
         #self.__path = path.replace('\\','/')
@@ -13,7 +11,8 @@ class JcampParser:
         self.__nb = self.__dxfile['blocks'] # Get the total number of blocks = The total number of scanned samples
         self.__list_of_blocks = self.__dxfile['children']  # Store all blocks within a a list
         self.__wl = self.__list_of_blocks[0]["x"] # Wavelengths/frequencies/range 
-    
+
+    def parse(self):
         # Start retreiving the data
         specs = np.zeros((self.__nb, len(self.__list_of_blocks[0]["y"])), dtype=float) # preallocate a np matrix for sotoring spectra
         self.idx = np.arange(self.__nb) # This list is designed to store samples name
@@ -60,7 +59,7 @@ class JcampParser:
         for match in re.findall(self.pattern, a):
                 elements_name.append(match[0])
 
-        ## Retrieve concentrationds
+        ## Retrieve concentrations
         df = self.metadata_['concentrations']
         cc = {}
         for i in range(self.metadata_.shape[0]):
@@ -105,7 +104,7 @@ class CsvParser:
 
 
     def __init__(self, file):
-        with NamedTemporaryFile(delete = False, suffix = ".dx") as tmp:
+        with NamedTemporaryFile(delete = False, suffix = ".csv") as tmp:
                 tmp.write(file.read())
                 self.file = tmp.name
 

src/utils/dim_reduction.py

-from packages import *
 from utils.data_handling import *
 
 

src/utils/eval_metrics.py

-from packages  import *
 
 class metrics:
+    from typing import Optional, List
+    from pandas import DataFrame
+
     def __init__(self, c:Optional[float] = None, cv:Optional[List] = None, t:Optional[List] = None, method = 'regression')-> DataFrame:
         phase = [c, cv, t]
         index = np.array(["train", "cv", "test"])

src/utils/hash.py

-from packages import *
 
 def create_hash(to_hash):
     #using the md5 hash function.

src/utils/miscellaneous.py

-from packages import *
+import streamlit as st
 
 
 # predict module

src/utils/regress.py

-from packages import *
 from utils import metrics, Snv, No_transformation, KF_CV, sel_ratio
 
 

src/utils/samsel.py

-from packages import *
 from typing import Sequence, Dict, Optional, Union
 
 class KS:
-    def __init__(self, x:Optional[Union[np.ndarray|DataFrame]], rset:Optional[Union[float|int]]):
+    from pandas import DataFrame
+    from numpy import ndarray
+    def __init__(self, x:Optional[Union[ndarray|DataFrame]], rset:Optional[Union[float|int]]):
+        from kennard_stone import train_test_split
         self.x = x
         self.ratio = rset
-        self._train, self._test = ks_train_test_split(self.x, train_size = self.ratio)
+        self._train, self._test = train_test_split(self.x, train_size = self.ratio)
     
     @property
     def calset(self):
@@ -13,7 +15,10 @@ class KS:
         return self.x, clu
     
 class RDM:
-    def __init__(self, x:Optional[Union[np.ndarray|DataFrame]], rset:Optional[Union[float|int]]):
+    from pandas import DataFrame
+    from numpy import ndarray
+    def __init__(self, x:Optional[Union[ndarray|DataFrame]], rset:Optional[Union[float|int]]):
+        from sklearn.model_selection import train_test_split
         self.x = x
         self.ratio = rset
         self._train, self._test = train_test_split(self.x, train_size = self.ratio)

src/utils/sql_connect.py

-from packages import pyodbc, json
 
 class SQL_Database():
-
     def __init__(self):
-    config_path = Path("../config/")
+        from json import load
+        from pathlib import Path
+        
+        config_path = Path("../config/")
         with open(config_path / 'config.json', 'r') as fh:
-            config = json.load(fh)
+            config = load(fh)
 
         self.driver = config['DRIVER']
         self.server = config['SERVER']
@@ -16,7 +17,8 @@ class SQL_Database():
         self.encrypt = config['ENCRYPT']
 
     def connect(self):
-        connection = pyodbc.connect(
+        from pyodbc import connect
+        connection = connect(
             f'Driver={self.driver};'
             f'Server={self.server};'
             f'Database={self.database};'

src/utils/visualize.py

-from  packages import * 
-
 
+import streamlit as st
 # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ predictions histogram ~~~~~~~~~~~~~~~~~~~~~~~~~~
 @st.cache_data
 def pred_hist(pred):