Update on.py
Browse files
on.py
CHANGED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import streamlit as st
|
| 2 |
+
import pandas as pd
|
| 3 |
+
import os
|
| 4 |
+
from glob import glob
|
| 5 |
+
|
| 6 |
+
# Function to get list of document IDs
|
| 7 |
+
def get_document_ids():
|
| 8 |
+
# Assuming 'abc' is the folder containing documents
|
| 9 |
+
document_ids = [file.split('_')[0] for file in os.listdir('abc') if file.endswith('.png')]
|
| 10 |
+
return list(set(document_ids))
|
| 11 |
+
|
| 12 |
+
# Function to load image based on selected document ID and page number
|
| 13 |
+
def load_image(image_path, document_id, page_number):
|
| 14 |
+
im_path = f"{image_path}{document_id}-{page_number-1}.png"
|
| 15 |
+
if os.path.exists(im_path):
|
| 16 |
+
return im_path
|
| 17 |
+
else:
|
| 18 |
+
return None
|
| 19 |
+
|
| 20 |
+
# Function to load dataframe based on selected document ID
|
| 21 |
+
def load_dataframe(auto_csv_path, document_id, page_number, cols):
|
| 22 |
+
csv_path = glob(f'{auto_csv_path}*{document_id}*auto.csv')
|
| 23 |
+
print(csv_path)
|
| 24 |
+
if len(csv_path)>0:
|
| 25 |
+
auto_df = pd.read_csv(csv_path[0])
|
| 26 |
+
auto_df_page = auto_df[auto_df['Page#']==page_number][cols]
|
| 27 |
+
return auto_df_page
|
| 28 |
+
else:
|
| 29 |
+
return None
|
| 30 |
+
|
| 31 |
+
def path_setting(inbound_df_path):
|
| 32 |
+
auto_csv_path = 'PhaseData/Batch1/NLP_batch/'
|
| 33 |
+
image_path = 'PhaseData/Data/output/images/'
|
| 34 |
+
inbound_df = pd.read_csv(inbound_df_path)
|
| 35 |
+
pif_list = list(inbound_df.pif_key.values)
|
| 36 |
+
return pif_list, image_path, auto_csv_path
|
| 37 |
+
|
| 38 |
+
def main():
|
| 39 |
+
inbound_df_path = 'inbound_issues_tempus_2_q2.csv'
|
| 40 |
+
display_cols = ['Biomarker Name Source', 'Biomarker Test Type', 'NLP Result','NLP Value', 'NLP Variant',
|
| 41 |
+
'Biomarker Test Result Value Numeric 1', 'Biomarker Test Result Value Unit 1',
|
| 42 |
+
'Biomarker Test Result Value Numeric 2', 'Biomarker Test Result Value Unit 2',
|
| 43 |
+
'Biomarker Test Threshold Value Numeric 1', 'Biomarker Test Threshold Value Unit1',
|
| 44 |
+
'Biomarker Test Threshold Value Numeric 2', 'Biomarker Test Threshold Value Unit2']
|
| 45 |
+
pif_list, image_path, auto_csv_path = path_setting(inbound_df_path)
|
| 46 |
+
|
| 47 |
+
st.set_page_config(layout="wide") # Set layout to wide
|
| 48 |
+
|
| 49 |
+
# Slider to adjust the width of the columns
|
| 50 |
+
col1_width = st.sidebar.slider("Width of First Column", 0.1, 10.0, 1.0, 0.1)
|
| 51 |
+
col2_width = st.sidebar.slider("Width of Second Column", 0.1, 10.0, 6.5, 0.1)
|
| 52 |
+
col3_width = st.sidebar.slider("Width of Third Column", 0.1, 10.0, 5.0, 0.1)
|
| 53 |
+
|
| 54 |
+
# Divide the screen into three vertical panels with specified widths
|
| 55 |
+
col1, col2, col3 = st.columns([col1_width, col2_width, col3_width])
|
| 56 |
+
|
| 57 |
+
# Document Selection Panel
|
| 58 |
+
with col1:
|
| 59 |
+
st.write("### Document Selection")
|
| 60 |
+
document_id = st.selectbox("Select Document ID", options=pif_list)
|
| 61 |
+
pages = [int(i.split('-')[-1].split('.')[0]) for i in glob(f"{image_path}{document_id}*.png")]
|
| 62 |
+
page_number = st.number_input("Page Number", min_value=1, max_value=len(pages), step=1, value=1)
|
| 63 |
+
|
| 64 |
+
# Display Image Panel
|
| 65 |
+
with col2:
|
| 66 |
+
st.write("### Display Image")
|
| 67 |
+
im_path = load_image(image_path, document_id, page_number)
|
| 68 |
+
if im_path:
|
| 69 |
+
# Wrap the image into a vertical slider
|
| 70 |
+
st.slider("", 0, 1, 0, 1, key="image_slider", value=0, orientation='vertical', format="")
|
| 71 |
+
st.image(im_path, use_column_width=True)
|
| 72 |
+
else:
|
| 73 |
+
st.write("Image not found")
|
| 74 |
+
|
| 75 |
+
# Display DataFrame Panel
|
| 76 |
+
with col3:
|
| 77 |
+
st.write("### Display DataFrame")
|
| 78 |
+
df = load_dataframe(auto_csv_path, document_id, page_number, display_cols)
|
| 79 |
+
if df is not None:
|
| 80 |
+
columns_to_display = st.multiselect("Select Columns to Display", df.columns)
|
| 81 |
+
if len(columns_to_display) > 0:
|
| 82 |
+
st.write(df[columns_to_display])
|
| 83 |
+
|
| 84 |
+
# Input area for comments and suggestions
|
| 85 |
+
st.subheader("Comments and Suggestions")
|
| 86 |
+
comment = st.text_area("Add your comment here")
|
| 87 |
+
suggestions = st.text_area("Add your suggestions here")
|
| 88 |
+
|
| 89 |
+
# Save comments and suggestions to CSV when submitted
|
| 90 |
+
if st.button("Submit"):
|
| 91 |
+
data = {
|
| 92 |
+
"Document ID": [document_id],
|
| 93 |
+
"Page": [page_number],
|
| 94 |
+
"Comment": [comment],
|
| 95 |
+
"Suggestions": [suggestions]
|
| 96 |
+
}
|
| 97 |
+
comments_df = pd.DataFrame(data)
|
| 98 |
+
comments_csv = "comments.csv"
|
| 99 |
+
if os.path.exists(comments_csv):
|
| 100 |
+
comments_df.to_csv(comments_csv, mode="a", header=False, index=False)
|
| 101 |
+
else:
|
| 102 |
+
comments_df.to_csv(comments_csv, index=False)
|
| 103 |
+
|
| 104 |
+
else:
|
| 105 |
+
st.write("No columns selected")
|
| 106 |
+
else:
|
| 107 |
+
st.write("DataFrame not found")
|
| 108 |
+
|
| 109 |
+
if __name__ == "__main__":
|
| 110 |
+
main()
|