app.py

import streamlit as st
from PIL import Image, ImageFilter
import numpy as np
import pandas as pd
from streamlit_cropper import st_cropper

# Mutation site headers removed 3614,
mutation_site_headers_actual = [
    3244, 3297, 3350, 3399, 3455, 3509, 3562, 
    3665, 3720, 3773, 3824, 3879, 3933, 3985, 4039,
    4089, 4145, 4190, 4245, 4298, 4349, 4402, 4455,
    4510, 4561, 4615, 4668, 4720, 4773, 4828, 4882
]

# Thresholds for each mutation site removed 3614: 0.091557752,
thresholds_actual = pd.Series({
    3244: 1.094293328, 3297: 0.924916122, 3350: 0.664586629, 3399: 0.91573613,
    3455: 1.300869714, 3509: 1.821975901, 3562: 1.178862418, 
    3665: 0.298697327, 3720: 0.58379781, 3773: 0.891088481, 3824: 1.145509641,
    3879: 0.81833191, 3933: 2.93084335, 3985: 1.593758847, 4039: 0.966055013,
    4089: 1.465671338, 4145: 0.30309335, 4190: 1.321615138, 4245: 1.709752495,
    4298: 0.868534701, 4349: 1.222907645, 4402: 0.58873557, 4455: 1.185522985,
    4510: 1.266797682, 4561: 1.109913024, 4615: 1.181106084, 4668: 1.408533949,
    4720: 0.714151142, 4773: 1.471959437, 4828: 0.95879943, 4882: 1.464503885
})

# Mutation site headers reordered: 4402 to 3244, 4882 to 4455
mutation_site_headers = [
    4402, 4349, 4298, 4245, 4190, 4145, 4089, 4039,
    3985, 3933, 3879, 3824, 3773, 3720, 3665,
    3562, 3509, 3455, 3399, 3350, 3297, 3244,  # 1–23
    4882, 4828, 4773, 4720, 4668, 4615, 4561, 4510, 4455   # 24–32
]

# 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
})
# === Utility functions ===

# Voyager ASCII 6-bit conversion table
voyager_table = {
    i: ch for i, ch in enumerate([
        ' ', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I',
        'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S',
        'T', 'U', 'V', 'W', 'X', 'Y', 'Z', '0', '1', '2',
        '3', '4', '5', '6', '7', '8', '9', '.', '(', ')',
        '+', '-', '*', '/', '=', '$', '!', ':', '%', '"',
        '#', '@', '\'', '?', '&'
    ])
}
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:
        val = reverse_voyager_table.get(char.upper(), 0)
        char_bits = [(val >> bit) & 1 for bit in range(5, -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), 6):
        chunk = bits[i:i+6]
        if len(chunk) < 6:
            chunk += [0] * (6 - len(chunk))
        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:
        img = img.resize((min_size, min_size))
    img = img.filter(ImageFilter.GaussianBlur(radius=1))
    return img

def image_to_binary_labels_rgb(img: Image.Image, max_pixels: int = 256) -> list[int]:
    img = clean_image(img)
    img.thumbnail((int(np.sqrt(max_pixels)), int(np.sqrt(max_pixels))))
    img_array = np.array(img)
    flat_pixels = img_array.reshape(-1, 3)

    bits = []
    for pixel in flat_pixels:
        for channel in pixel:
            channel_bits = [(channel >> bit) & 1 for bit in range(7, -1, -1)]
            bits.extend(channel_bits)
    return bits

def binary_labels_to_rgb_image(binary_labels: list[int], width: int = None, height: int = None) -> Image.Image:
    total_pixels = len(binary_labels) // 24
    if width is None or height is None:
        side = int(np.ceil(np.sqrt(total_pixels)))
        width = height = side

    needed_pixels = width * height
    needed_bits = needed_pixels * 24
    if len(binary_labels) < needed_bits:
        binary_labels += [0] * (needed_bits - len(binary_labels))

    pixels = []
    for i in range(0, needed_bits, 24):
        r_bits = binary_labels[i:i+8]
        g_bits = binary_labels[i+8:i+16]
        b_bits = binary_labels[i+16:i+24]
        r = sum(b << (7-j) for j, b in enumerate(r_bits))
        g = sum(b << (7-j) for j, b in enumerate(g_bits))
        b = sum(b << (7-j) for j, b in enumerate(b_bits))
        pixels.append((r, g, b))

    array = np.array(pixels, dtype=np.uint8).reshape((height, width, 3))
    img = Image.fromarray(array, mode='RGB')
    return img

# === Streamlit App ===

st.title("ASCII & Binary Label Converter")
tab1, tab2, tab3 = st.tabs(["Text to Binary Labels", "Image to Binary Labels", "EF → Binary"])

# Tab 1: Text to Binary
with tab1:
    user_input = st.text_input("Enter text", value="DNA")
    if user_input:
        ascii_codes = [ord(c) for c in user_input]
        binary_labels = string_to_binary_labels(user_input)

        st.subheader("ASCII Codes")
        st.write(ascii_codes)

        st.subheader("Binary Labels per Character")
        grouped = [binary_labels[i:i+6] for i in range(0, len(binary_labels), 6)]
        for i, bits in enumerate(grouped):
            st.write(f"'{user_input[i]}' → {bits}")

        st.subheader("Binary Labels (31-bit groups)")
        groups = []
        for i in range(0, len(binary_labels), 31):
            group = binary_labels[i:i+31]
            group += [0] * (31 - len(group))
            groups.append(group + [sum(group)])

        df_31 = pd.DataFrame(groups, columns=[str(h) for h in mutation_site_headers] + ["Edited Sites"])
        st.dataframe(df_31)
        st.download_button("Download as CSV", df_31.to_csv(index=False), "text_32_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])
        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.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 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")

# Tab 3: EF → Binary
with st.tabs(["Text to Binary Labels", "Image to Binary Labels", "EF → Binary"])[2]:
    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.")
    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 <= 4455])

    if ef_file:
        ef_df = pd.read_csv(ef_file, header=None)
        ef_df.columns = [str(site) for site in ascending_input_headers]
    else:
        ef_df = pd.DataFrame(columns=[str(site) for site in ascending_input_headers])

    edited_df = st.data_editor(ef_df, num_rows="dynamic")

    if st.button("Convert to Binary Labels"):
        # Use ascending headers to create binary first
        binary_part = pd.DataFrame()
        for col in ascending_input_headers:
            col_str = str(col)
            threshold = thresholds[col]
            binary_part[col_str] = (edited_df[col_str].astype(float) >= threshold).astype(int)

        # Rearranged for output: custom order from mutation_site_headers
        binary_reordered = binary_part[[str(h) for h in mutation_site_headers if str(h) in binary_part.columns]]

        def color_binary(val):
            if val == 1: return "background-color: lightgreen"
            if val == 0: return "background-color: lightcoral"
            return ""

        st.subheader("Binary Labels (Reordered 4402→3244, 4882→4455)")
        styled = binary_reordered.style.applymap(color_binary)
        st.dataframe(styled)
        st.download_button("Download CSV", binary_reordered.to_csv(index=False), "ef_binary_labels.csv")

        # Reconstruct original string from binary values (flatten row-wise)
        for i, row in binary_reordered.iterrows():
            binary_sequence = row.tolist()
            text = binary_labels_to_string(binary_sequence)
            st.write(f"Row {i+1} decoded string: {text}")

# # 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)