From 4786ec3661e9f1a1cbc2289f7865b051e17b0def Mon Sep 17 00:00:00 2001
From: DIANE <abderrahim.diane@cefe.cnrs.fr>
Date: Thu, 10 Oct 2024 15:57:39 +0200
Subject: [PATCH] miscellaneous.py
---
src/utils/miscellaneous.py | 104 +++++++++++++++++++++++++++++++++++++
1 file changed, 104 insertions(+)
create mode 100644 src/utils/miscellaneous.py
diff --git a/src/utils/miscellaneous.py b/src/utils/miscellaneous.py
new file mode 100644
index 0000000..d8ac4b4
--- /dev/null
+++ b/src/utils/miscellaneous.py
@@ -0,0 +1,104 @@
+from packages import *
+
+
+# predict module
+def prediction(NIRS_csv, qsep, qhdr, model):
+ # hdr var correspond to column header True or False in the CSV
+ if qhdr == 'yes':
+ col = 0
+ else:
+ col = False
+ X_test = read_csv(NIRS_csv, sep=qsep, index_col=col)
+ Y_preds = model.predict(X_test)
+ # Y_preds = X_test
+ return Y_preds
+
+
+# function that create a download button - needs the data to save and the file name to store to
+def download_results(data, export_name):
+ with open(data) as f:
+ st.download_button('Download', f, export_name, type='primary')
+
+@st.cache_data(show_spinner =True)
+def data_split(x, y):
+ # Split data into training and test sets using the kennard_stone method and correlation metric, 25% of data is used for testing
+ train_index, test_index = train_test_split_idx(x , y = y, method = "kennard_stone", metric = "correlation", test_size = 0.25, random_state = 42)
+ # Assign data to training and test sets
+ X_train, y_train = DataFrame(x.iloc[train_index,:]), y.iloc[train_index]
+ X_test, y_test = DataFrame(x.iloc[test_index,:]), y.iloc[test_index]
+ return X_train, X_test, y_train, y_test, train_index, test_index
+
+## descriptive stat
+@st.cache_data(show_spinner =True)
+def desc_stats(x):
+ a = {}
+ a['N samples'] = x.shape[0]
+ a['Min'] = np.min(x)
+ a['Max'] = np.max(x)
+ a['Mean'] = np.mean(x)
+ a['Median'] = np.median(x)
+ a['S'] = np.std(x)
+ a['RSD'] = np.std(x)*100/np.mean(x)
+ a['Skew'] = skew(x, axis=0, bias=True)
+ a['Kurt'] = kurtosis(x, axis=0, bias=True)
+ return a
+
+
+
+def ObjectHash(current = None, add = None):
+ def DatatoStr(data):
+ from pandas import DataFrame, Series
+ import numpy as np
+ """Hash various data types using MD5."""
+
+ # Convert to a string representation
+ if isinstance(data, DataFrame):
+ data_str = data.to_string()
+ elif isinstance(data, Series):
+ data_str = data.to_string()
+ elif isinstance(data, np.ndarray):
+ data_str = np.array2string(data, separator=',')
+ elif isinstance(data, (list, tuple)):
+ data_str = str(data)
+ elif isinstance(data, dict):
+ # Ensure consistent order for dict items
+ data_str = str(sorted(data.items()))
+ elif isinstance(data, (int, float, str, bool)):
+ data_str = str(data)
+ elif isinstance(data, bytes):
+ data_str = data.decode('utf-8', 'ignore') # Decode bytes to string
+ elif isinstance(data, str): # Check if it's a string representing file content
+ data_str = data
+ else:
+ raise TypeError(f"Unsupported data type: {type(data)}")
+
+ # Encode the string to bytes
+ data_bytes = data_str.encode()
+ return str(data_bytes)
+
+
+ import xxhash
+ if current == None and add == None:
+ object = "None"
+ print('Insert the object for which you want to compute the hash value.')
+ elif current != None and add != None:
+ object = DatatoStr(current)+ DatatoStr(add)
+ elif current == None and add != None:
+ object = DatatoStr(add)
+ elif current != None and add == None:
+ object = DatatoStr(current)
+
+ # Compute the MD5 hash
+
+ md5_hash = xxhash.xxh32(object).hexdigest()
+ return str(md5_hash)
+
+
+
+def JointoMain():
+ import os
+ for i in ['utils','style']:
+ import sys
+ sys.path.append(os.path.join(os.path.dirname(__file__), i))
+
+#
\ No newline at end of file
--
GitLab