Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -14,22 +14,24 @@ uploaded_file2 = st.file_uploader("Upload Second Excel File", type=["xlsx"])
|
|
| 14 |
|
| 15 |
if uploaded_file1 and uploaded_file2:
|
| 16 |
try:
|
| 17 |
-
# Read
|
| 18 |
df1 = pd.read_excel(uploaded_file1, header=1)
|
| 19 |
df2 = pd.read_excel(uploaded_file2, header=1)
|
| 20 |
|
| 21 |
-
# Automatically
|
| 22 |
id_col = df1.columns[0]
|
| 23 |
name_col = df1.columns[1]
|
| 24 |
repeat_cols = df1.columns[2:]
|
| 25 |
|
|
|
|
|
|
|
|
|
|
| 26 |
records = []
|
| 27 |
|
| 28 |
for _, row1 in df1.iterrows():
|
| 29 |
entry_id = row1[id_col]
|
| 30 |
protein_name = row1[name_col]
|
| 31 |
|
| 32 |
-
# Match in second file
|
| 33 |
match = df2[(df2[id_col] == entry_id) & (df2[name_col] == protein_name)]
|
| 34 |
if match.empty:
|
| 35 |
continue
|
|
@@ -43,27 +45,31 @@ if uploaded_file1 and uploaded_file2:
|
|
| 43 |
records.append({
|
| 44 |
id_col: entry_id,
|
| 45 |
name_col: protein_name,
|
| 46 |
-
"Repeat": repeat,
|
| 47 |
"Frequency File 1": freq1,
|
| 48 |
"Frequency File 2": freq2,
|
| 49 |
"Difference": diff
|
| 50 |
})
|
| 51 |
|
| 52 |
-
|
| 53 |
-
|
|
|
|
| 54 |
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
|
| 59 |
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
|
|
|
|
|
|
|
| 67 |
|
| 68 |
except Exception as e:
|
| 69 |
-
st.error(f"⚠️ Error: {e}")
|
|
|
|
|
|
| 14 |
|
| 15 |
if uploaded_file1 and uploaded_file2:
|
| 16 |
try:
|
| 17 |
+
# Read Excel files (header starts from second row)
|
| 18 |
df1 = pd.read_excel(uploaded_file1, header=1)
|
| 19 |
df2 = pd.read_excel(uploaded_file2, header=1)
|
| 20 |
|
| 21 |
+
# Automatically get ID and Name column
|
| 22 |
id_col = df1.columns[0]
|
| 23 |
name_col = df1.columns[1]
|
| 24 |
repeat_cols = df1.columns[2:]
|
| 25 |
|
| 26 |
+
# Ensure all column names are strings
|
| 27 |
+
repeat_cols = [str(col) for col in repeat_cols]
|
| 28 |
+
|
| 29 |
records = []
|
| 30 |
|
| 31 |
for _, row1 in df1.iterrows():
|
| 32 |
entry_id = row1[id_col]
|
| 33 |
protein_name = row1[name_col]
|
| 34 |
|
|
|
|
| 35 |
match = df2[(df2[id_col] == entry_id) & (df2[name_col] == protein_name)]
|
| 36 |
if match.empty:
|
| 37 |
continue
|
|
|
|
| 45 |
records.append({
|
| 46 |
id_col: entry_id,
|
| 47 |
name_col: protein_name,
|
| 48 |
+
"Repeat": str(repeat),
|
| 49 |
"Frequency File 1": freq1,
|
| 50 |
"Frequency File 2": freq2,
|
| 51 |
"Difference": diff
|
| 52 |
})
|
| 53 |
|
| 54 |
+
if records:
|
| 55 |
+
result_df = pd.DataFrame(records)
|
| 56 |
+
result_df = result_df.sort_values(by="Difference", ascending=False)
|
| 57 |
|
| 58 |
+
output = BytesIO()
|
| 59 |
+
with pd.ExcelWriter(output, engine="openpyxl") as writer:
|
| 60 |
+
result_df.to_excel(writer, index=False)
|
| 61 |
+
output.seek(0)
|
| 62 |
|
| 63 |
+
st.success("✅ Comparison complete! Only changed repeats are included.")
|
| 64 |
+
st.download_button(
|
| 65 |
+
label="📥 Download Changed Repeats Excel",
|
| 66 |
+
data=output,
|
| 67 |
+
file_name="changed_protein_repeats.xlsx",
|
| 68 |
+
mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
|
| 69 |
+
)
|
| 70 |
+
else:
|
| 71 |
+
st.info("No changes in repeat frequencies were found.")
|
| 72 |
|
| 73 |
except Exception as e:
|
| 74 |
+
st.error(f"⚠️ Error: {e}")
|
| 75 |
+
|