Update app.py

app.py

@@ -10,6 +10,26 @@ import networkx as nx
 
 st.set_page_config(layout="wide")
 
+# Add custom CSS for floating image
+st.markdown("""
+    <style>
+    .floating-image {
+        position: fixed;
+        bottom: 20px;
+        right: 20px;
+        z-index: 9999;
+        width: 150px;
+        height: auto;
+        border-radius: 10px;
+        box-shadow: 0 4px 6px rgba(0, 0, 0, 0.3);
+        transition: transform 0.3s ease;
+    }
+    .floating-image:hover {
+        transform: scale(1.1);
+    }
+    </style>
+    """, unsafe_allow_html=True)
+
 def parse_voynich_word(word):
     """Parse a Voynich word into individual characters - NO assumptions about digraphs"""
     if not word or word.strip() == '':
@@ -143,12 +163,39 @@ def get_download_link_csv(df, filename):
 
 st.title("Voynich Manuscript Analyzer")
 st.write("Upload your CSV file to discover potential patterns and character distributions.")
-st.write("**Bottom-up analysis**: Each character is treated independently - no assumptions about digraphs")
+
+# Add floating image uploader
+floating_image_file = st.file_uploader("Upload a floating image (optional)", 
+                                       type=['png', 'jpg', 'jpeg', 'gif'],
+                                       key="floating_image")
+
+if floating_image_file is not None:
+    # Convert image to base64 for embedding
+    import base64
+    image_bytes = floating_image_file.read()
+    image_b64 = base64.b64encode(image_bytes).decode()
+    
+    # Display floating image
+    st.markdown(f"""
+        <img src="data:image/png;base64,{image_b64}" class="floating-image" alt="Floating image">
+        """, unsafe_allow_html=True)
 
 uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
 
 if uploaded_file is not None:
-    df = pd.read_csv(uploaded_file, header=None)
+    # Read the entire file as text first
+    uploaded_file.seek(0)
+    content = uploaded_file.read().decode('utf-8')
+    
+    # Split into lines (handle both \n and \r\n)
+    lines = content.replace('\r\n', '\n').replace('\r', '\n').strip().split('\n')
+    # Filter out empty lines - only keep lines with actual content
+    lines = [line for line in lines if line.strip()]
+    data = [line.split(',') for line in lines]
+    
+    # Create DataFrame from parsed data
+    df = pd.DataFrame(data)
+    
     words, chars_list, char_positions, char_connections, word_positions, line_word_map = analyze_csv(df)
     
     st.subheader("Basic Statistics")
@@ -177,7 +224,10 @@ if uploaded_file is not None:
             char_bigrams[bigram] += 1
     
     char_bigram_df = pd.DataFrame([
-        {'Bigram': ''.join(bigram), 'Char1': bigram[0], 'Char2': bigram[1], 'Count': count}
+        {'Bigram': ''.join(str(c) for c in bigram), 
+         'Char1': str(bigram[0]), 
+         'Char2': str(bigram[1]), 
+         'Count': int(count)}
         for bigram, count in char_bigrams.most_common(30)
     ])
     st.dataframe(char_bigram_df)
@@ -193,7 +243,7 @@ if uploaded_file is not None:
             char_trigrams[trigram] += 1
     
     char_trigram_df = pd.DataFrame([
-        {'Trigram': ''.join(trigram), 'Count': count}
+        {'Trigram': ''.join(str(c) for c in trigram), 'Count': int(count)}
         for trigram, count in char_trigrams.most_common(30)
     ])
     st.dataframe(char_trigram_df)
@@ -206,7 +256,7 @@ if uploaded_file is not None:
         word_bigrams[bigram] += 1
             
     word_bigram_df = pd.DataFrame([
-        {'Word1': bigram[0], 'Word2': bigram[1], 'Count': count}
+        {'Word1': str(bigram[0]), 'Word2': str(bigram[1]), 'Count': int(count)}
         for bigram, count in word_bigrams.most_common(20)
     ])
     st.dataframe(word_bigram_df)
@@ -219,7 +269,10 @@ if uploaded_file is not None:
         word_trigrams[trigram] += 1
             
     word_trigram_df = pd.DataFrame([
-        {'Word1': trigram[0], 'Word2': trigram[1], 'Word3': trigram[2], 'Count': count}
+        {'Word1': str(trigram[0]), 
+         'Word2': str(trigram[1]), 
+         'Word3': str(trigram[2]), 
+         'Count': int(count)}
         for trigram, count in word_trigrams.most_common(20)
     ])
     st.dataframe(word_trigram_df)
@@ -370,9 +423,11 @@ if uploaded_file is not None:
     st.subheader("Overall Character Frequency")
     all_chars_flat = [char for chars in chars_list for char in chars]
     char_freq = Counter(all_chars_flat)
+    total_chars = len(all_chars_flat)
     
     fig_freq = plt.figure(figsize=(12, 6))
     char_freq_df = pd.DataFrame(char_freq.most_common(), columns=['Character', 'Count'])
+    char_freq_df['Percentage'] = (char_freq_df['Count'] / total_chars * 100).round(2)
     plt.bar(char_freq_df['Character'], char_freq_df['Count'])
     plt.title("Character Frequency Distribution")
     plt.xlabel("Character")
@@ -380,6 +435,7 @@ if uploaded_file is not None:
     plt.xticks(rotation=45)
     st.pyplot(fig_freq)
     st.dataframe(char_freq_df)
+    st.markdown(get_download_link_csv(char_freq_df, "character_frequency.csv"), unsafe_allow_html=True)
     
     # Character Position Heatmap
     st.subheader("Character Position Heatmap")
@@ -477,7 +533,9 @@ if uploaded_file is not None:
             ngrams[ngram] += 1
     
     ngram_df = pd.DataFrame([
-        {'Pattern': ''.join(ngram), 'Count': count, 'Percentage': f"{count/len(chars_list)*100:.2f}%"}
+        {'Pattern': ''.join(str(c) for c in ngram), 
+         'Count': int(count), 
+         'Percentage': f"{count/len(chars_list)*100:.2f}%"}
         for ngram, count in ngrams.most_common(30)
     ])
     st.dataframe(ngram_df)