Update Quality_Control.py

Quality_Control.py

@@ -22,6 +22,7 @@ from bokeh.io import curdoc
 from bokeh.models import Span, Label
 from bokeh.models import ColumnDataSource, Button
 from my_modules import *
+from datasets import load_dataset
 
 #Silence FutureWarnings & UserWarnings
 warnings.filterwarnings('ignore', category= FutureWarning)
@@ -54,7 +55,7 @@ print(selected_metadata_files)'''
 
 
     
-base_dir = '/mnt/data/wetransfer_data-zip_2024-05-17_1431'
+base_dir = '/Users/harshithakolipaka/Downloads/wetransfer_data-zip_2024-05-17_1431'
 set_path = 'test'
 selected_metadata_files = "['Slide_B_DD1s1.one_1.tif.csv', 'Slide_B_DD1s1.one_2.tif.csv']"
 ls_samples = "['Ashlar_Exposure_Time.csv', 'new_data.csv', 'DD3S1.csv', 'DD3S2.csv', 'DD3S3.csv', 'TMA.csv']"
@@ -238,9 +239,9 @@ ls_samples
 
 
 # In[29]:
-
-
-df = pd.read_csv(os.path.join(input_data_dir, ls_samples[0]),index_col = 0, nrows = 1)
+path = os.path.join(input_data_dir, ls_samples[0])
+df = load_dataset('csv', data_files = path )
+#df = pd.read_csv(os.path.join(input_data_dir, ls_samples[0]),index_col = 0, nrows = 1)
 df.head(10)
 
 
@@ -249,7 +250,7 @@ df.head(10)
 
 # First gather information on expected headers using first file in ls_samples
 # Read in the first row of the file corresponding to the first sample (index = 0) in ls_samples
-df = pd.read_csv(os.path.join(input_data_dir, ls_samples[0]) , index_col = 0, nrows = 1)
+#df = pd.read_csv(os.path.join(input_data_dir, ls_samples[0]) , index_col = 0, nrows = 1)
 
 
 # Make sure the file was imported correctly
@@ -341,6 +342,7 @@ for sample in ls_samples:
     
     try:
         # Read the CSV file
+        df = load_dataset("csv", data_files = file_path)
         df = pd.read_csv(file_path, index_col=0)
         # Check if the DataFrame is empty, if so, don't continue trying to process df and remove it