Update app.py

app.py

@@ -33,16 +33,8 @@ mutation_site_headers = [
 ]
 
 # Thresholds reordered accordingly
-thresholds = pd.Series({
-    4402: 0.58873557, 4349: 1.222907645, 4298: 0.868534701, 4245: 1.709752495,
-    4190: 1.321615138, 4145: 0.30309335, 4089: 1.465671338, 4039: 0.966055013,
-    3985: 1.593758847, 3933: 2.93084335, 3879: 0.81833191, 3824: 1.145509641,
-    3773: 0.891088481, 3720: 0.58379781, 3665: 0.298697327, 
-    3562: 1.178862418, 3509: 1.821975901, 3455: 1.300869714, 3399: 0.91573613,
-    3350: 0.664586629, 3297: 0.924916122, 3244: 1.094293328,
-    4882: 1.464503885, 4828: 0.95879943, 4773: 1.471959437, 4720: 0.714151142,
-    4668: 1.408533949, 4615: 1.181106084, 4561: 1.109913024, 4510: 1.266797682, 4455: 1.185522985
-})
+thresholds = pd.Series({h: thresholds_actual[h] for h in mutation_site_headers})
+
 # === Utility functions ===
 
 # Voyager ASCII 6-bit conversion table
@@ -58,8 +50,6 @@ voyager_table = {
 }
 reverse_voyager_table = {v: k for k, v in voyager_table.items()}
 
-# === Utility functions ===
-
 def string_to_binary_labels(s: str) -> list[int]:
     bits = []
     for char in s:
@@ -77,25 +67,7 @@ def binary_labels_to_string(bits: list[int]) -> str:
         val = sum(b << (5 - j) for j, b in enumerate(chunk))
         chars.append(voyager_table.get(val, '?'))
     return ''.join(chars)
-    
-# def string_to_binary_labels(s: str) -> list[int]:
-#     bits = []
-#     for char in s:
-#         ascii_code = ord(char)
-#         char_bits = [(ascii_code >> bit) & 1 for bit in range(7, -1, -1)]
-#         bits.extend(char_bits)
-#     return bits
-
-# def binary_labels_to_string(bits: list[int]) -> str:
-#     chars = []
-#     for i in range(0, len(bits), 8):
-#         byte = bits[i:i+8]
-#         if len(byte) < 8:
-#             byte += [0] * (8 - len(byte))
-#         ascii_val = sum(b << (7 - j) for j, b in enumerate(byte))
-#         chars.append(chr(ascii_val))
-#     return ''.join(chars)
-    
+
 def clean_image(img: Image.Image, min_size: int = 256) -> Image.Image:
     img = img.convert("RGB")
     if img.width < min_size or img.height < min_size:
@@ -172,52 +144,32 @@ with tab1:
         st.dataframe(df)
         st.download_button("Download as CSV", df.to_csv(index=False), "text_31_binary_labels.csv")
 
-        # Additional table with ascending mutation site headers (3244 to 4455)
-        ascending_headers = sorted([h for h in mutation_site_headers if h <= 4455])
+        ascending_headers = sorted(mutation_site_headers_actual)
         df_sorted = df[[str(h) for h in ascending_headers if str(h) in df.columns]]
-        st.subheader("Binary Labels (Ascending Order 3244 → 4455)")
+        st.subheader("Binary Labels (Ascending Order 3244 → 4882)")
         st.dataframe(df_sorted)
         st.download_button("Download Ascending Order CSV", df_sorted.to_csv(index=False), "text_binary_labels_ascending.csv")
 
-
-        # st.subheader("Binary Labels (27-bit groups)")
-        # groups = []
-        # for i in range(0, len(binary_labels), 27):
-        #     group = binary_labels[i:i+27]
-        #     group += [0] * (27 - len(group))
-        #     groups.append(group + [sum(group)])
-
-        # df_27 = pd.DataFrame(groups, columns=[str(h) for h in mutation_site_headers] + ["Edited Sites"])
-        # st.dataframe(df_27)
-        # st.download_button("Download as CSV", df_27.to_csv(index=False), "text_27_binary_labels.csv")
-
-# Tab 3: EF → Binary
+# Tab 2: EF → Binary
 with tab2:
     st.write("Upload an Editing Frequency CSV or enter manually:")
-    st.write("**Note:** Please upload CSV files **without column headers**, in ascending order from 3244 to 4455.")
+    st.write("**Note:** Please upload CSV files **without column headers**, in ascending order from 3244 to 4882.")
     ef_file = st.file_uploader("Upload EF CSV", type=["csv"], key="ef")
 
-    ascending_input_headers = sorted([h for h in mutation_site_headers if 3244 <= h <= 4402])
-    high_index_headers = sorted([h for h in mutation_site_headers if h >= 4455])
-
     if ef_file:
         ef_df = pd.read_csv(ef_file, header=None)
-        ef_df.columns = [str(site) for site in ascending_input_headers]
-        for h in high_index_headers:
-            ef_df[str(h)] = 0  # add dummy columns for high index as 0
+        ef_df.columns = [str(site) for site in sorted(mutation_site_headers_actual)]
     else:
-        ef_df = pd.DataFrame(columns=[str(site) for site in ascending_input_headers + high_index_headers])
+        ef_df = pd.DataFrame(columns=[str(site) for site in sorted(mutation_site_headers_actual)])
 
     edited_df = st.data_editor(ef_df, num_rows="dynamic")
 
     if st.button("Convert to Binary Labels"):
         binary_part = pd.DataFrame()
-        for col in ascending_input_headers:
+        for col in sorted(mutation_site_headers_actual):
             col_str = str(col)
-            threshold = thresholds[col]
+            threshold = thresholds_actual[col]
             binary_part[col_str] = (edited_df[col_str].astype(float) >= threshold).astype(int)
-        for col in high_index_headers:
-            binary_part[str(col)] = 0
 
         binary_reordered = binary_part[[str(h) for h in mutation_site_headers if str(h) in binary_part.columns]]
 
@@ -236,90 +188,6 @@ with tab2:
         st.subheader("Decoded String (continuous across rows)")
         st.write(decoded_string)
 
-        binary_ascending = binary_part[[str(h) for h in ascending_input_headers if str(h) in binary_part.columns]]
-        st.subheader("Binary Labels (Ascending 3244→4455)")
-        st.dataframe(binary_ascending)
-        st.download_button("Download Ascending Order CSV", binary_ascending.to_csv(index=False), "ef_binary_labels_ascending.csv")
-
-
-# # Tab 3: EF → Binary
-# with tab3:
-#     st.write("Upload an Editing Frequency CSV or enter manually:")
-#     st.write("**Note:** Please upload CSV files **without column headers**. Just the 31 editing frequencies per row.")
-#     ef_file = st.file_uploader("Upload EF CSV", type=["csv"], key="ef")
-    
-#     if ef_file:
-#         # Read CSV without headers and assign mutation site headers
-#         ef_df = pd.read_csv(ef_file, header=None)
-#         ef_df.columns = [str(site) for site in mutation_site_headers]
-#     else:
-#         ef_df = pd.DataFrame(columns=[str(site) for site in mutation_site_headers])
-
-
-#     edited_df = st.data_editor(ef_df, num_rows="dynamic")
-
-#     if st.button("Convert to Binary Labels"):
-#         int_map = {str(k): k for k in thresholds.index}
-#         matching_cols = [col for col in edited_df.columns if col in int_map]
-
-#         binary_part = pd.DataFrame()
-#         for col in matching_cols:
-#             col_threshold = thresholds[int_map[col]]
-#             binary_part[col] = (edited_df[col].astype(float) >= col_threshold).astype(int)
-
-#         non_binary_part = edited_df.drop(columns=matching_cols, errors='ignore')
-#         binary_df = pd.concat([non_binary_part, binary_part], axis=1)
-
-#         def color_binary(val):
-#             if val == 1: return "background-color: lightgreen"
-#             if val == 0: return "background-color: lightcoral"
-#             return ""
-
-#         st.subheader("Binary Labels")
-#         styled = binary_df.style.applymap(color_binary, subset=matching_cols)
-#         st.dataframe(styled)
-#         st.download_button("Download CSV", binary_df.to_csv(index=False), "ef_binary_labels.csv")
-
-#         # Convert to bitstrings and strings
-#         binary_strings = []
-#         decoded_strings = []
-#         for _, row in binary_part.iterrows():
-#             bitlist = row.values.tolist()
-#             bitstring = ''.join(str(b) for b in bitlist)
-#             binary_strings.append(bitstring)
-#             decoded_strings.append(binary_labels_to_string(bitlist))
-
-#         st.subheader("Binary as Bitstrings")
-#         for b in binary_strings:
-#             st.code(b)
-
-#         st.subheader("Decoded Voyager Strings")
-#         for s in decoded_strings:
-#             st.write(s)
-
-
-# # Tab 2: Image to Binary
-# with tab2:
-#     uploaded = st.file_uploader("Upload an image (jpg/png)", type=["jpg", "jpeg", "png"])
-#     if uploaded:
-#         img = Image.open(uploaded)
-#         st.image(img, caption="Original", use_column_width=True)
-#         cropped = st_cropper(img, realtime_update=True, box_color="blue", aspect_ratio=None)
-#         st.image(cropped, caption="Cropped", use_column_width=True)
-
-#         max_pixels = st.slider("Max pixels to encode", 32, 1024, 256, 32)
-#         binary_labels = image_to_binary_labels_rgb(cropped, max_pixels=max_pixels)
-
-#         st.subheader("Binary Labels from Image")
-#         groups = []
-#         for i in range(0, len(binary_labels), 32):
-#             group = binary_labels[i:i+32]
-#             group += [0] * (32 - len(group))
-#             groups.append(group + [sum(group)])
-#         df = pd.DataFrame(groups, columns=[str(h) for h in mutation_site_headers] + ["Edited Sites"])
-#         st.dataframe(df)
-
-#         st.subheader("Reconstructed Image")
-#         recon = binary_labels_to_rgb_image(binary_labels)
-#         st.image(recon, caption="Reconstructed", use_column_width=True)
-#         st.download_button("Download CSV", df.to_csv(index=False), "image_binary_labels.csv")
+        st.subheader("Binary Labels (Ascending 3244→4882)")
+        st.dataframe(binary_part)
+        st.download_button("Download Ascending Order CSV", binary_part.to_csv(index=False), "ef_binary_labels_ascending.csv")