Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -14,18 +14,15 @@ uploaded_file2 = st.file_uploader("Upload Second Excel File", type=["xlsx"])
|
|
| 14 |
|
| 15 |
if uploaded_file1 and uploaded_file2:
|
| 16 |
try:
|
| 17 |
-
# Read files: header is in the first row (index 0)
|
| 18 |
df1 = pd.read_excel(uploaded_file1, header=0)
|
| 19 |
df2 = pd.read_excel(uploaded_file2, header=0)
|
| 20 |
|
| 21 |
-
# Ensure column names are strings
|
| 22 |
df1.columns = df1.columns.astype(str)
|
| 23 |
df2.columns = df2.columns.astype(str)
|
| 24 |
|
| 25 |
-
# Get ID and Name columns
|
| 26 |
id_col = df1.columns[0]
|
| 27 |
name_col = df1.columns[1]
|
| 28 |
-
repeat_columns = df1.columns[2:]
|
| 29 |
|
| 30 |
differences = []
|
| 31 |
|
|
@@ -43,34 +40,46 @@ if uploaded_file1 and uploaded_file2:
|
|
| 43 |
freq1 = row1[repeat_col]
|
| 44 |
freq2 = row2[repeat_col]
|
| 45 |
|
| 46 |
-
if pd.isna(freq1) or pd.isna(freq2):
|
| 47 |
continue
|
| 48 |
|
| 49 |
if freq1 != freq2:
|
| 50 |
diff = abs(freq1 - freq2)
|
|
|
|
| 51 |
differences.append({
|
| 52 |
id_col: entry_id,
|
| 53 |
name_col: protein_name,
|
| 54 |
"Repeat": repeat_col,
|
| 55 |
"Frequency File 1": freq1,
|
| 56 |
"Frequency File 2": freq2,
|
| 57 |
-
"Difference": diff
|
|
|
|
| 58 |
})
|
| 59 |
|
| 60 |
if differences:
|
| 61 |
result_df = pd.DataFrame(differences)
|
| 62 |
result_df = result_df.sort_values(by="Difference", ascending=False)
|
| 63 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
output = BytesIO()
|
| 65 |
with pd.ExcelWriter(output, engine='openpyxl') as writer:
|
| 66 |
-
|
| 67 |
output.seek(0)
|
| 68 |
|
| 69 |
st.success("β
Comparison complete. Showing only changed repeats.")
|
| 70 |
st.download_button(
|
| 71 |
label="π₯ Download Excel",
|
| 72 |
data=output,
|
| 73 |
-
file_name="
|
| 74 |
mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
|
| 75 |
)
|
| 76 |
else:
|
|
|
|
| 14 |
|
| 15 |
if uploaded_file1 and uploaded_file2:
|
| 16 |
try:
|
|
|
|
| 17 |
df1 = pd.read_excel(uploaded_file1, header=0)
|
| 18 |
df2 = pd.read_excel(uploaded_file2, header=0)
|
| 19 |
|
|
|
|
| 20 |
df1.columns = df1.columns.astype(str)
|
| 21 |
df2.columns = df2.columns.astype(str)
|
| 22 |
|
|
|
|
| 23 |
id_col = df1.columns[0]
|
| 24 |
name_col = df1.columns[1]
|
| 25 |
+
repeat_columns = df1.columns[2:]
|
| 26 |
|
| 27 |
differences = []
|
| 28 |
|
|
|
|
| 40 |
freq1 = row1[repeat_col]
|
| 41 |
freq2 = row2[repeat_col]
|
| 42 |
|
| 43 |
+
if pd.isna(freq1) or pd.isna(freq2) or freq1 == 0:
|
| 44 |
continue
|
| 45 |
|
| 46 |
if freq1 != freq2:
|
| 47 |
diff = abs(freq1 - freq2)
|
| 48 |
+
pct_change = ((freq2 - freq1) / freq1) * 100
|
| 49 |
differences.append({
|
| 50 |
id_col: entry_id,
|
| 51 |
name_col: protein_name,
|
| 52 |
"Repeat": repeat_col,
|
| 53 |
"Frequency File 1": freq1,
|
| 54 |
"Frequency File 2": freq2,
|
| 55 |
+
"Difference": diff,
|
| 56 |
+
"%age Change": pct_change
|
| 57 |
})
|
| 58 |
|
| 59 |
if differences:
|
| 60 |
result_df = pd.DataFrame(differences)
|
| 61 |
result_df = result_df.sort_values(by="Difference", ascending=False)
|
| 62 |
|
| 63 |
+
# Style for Excel (green for +, red for -)
|
| 64 |
+
def color_pct(val):
|
| 65 |
+
if val > 0:
|
| 66 |
+
return 'color: green'
|
| 67 |
+
elif val < 0:
|
| 68 |
+
return 'color: red'
|
| 69 |
+
return ''
|
| 70 |
+
|
| 71 |
+
styled_df = result_df.style.applymap(color_pct, subset=["%age Change"])
|
| 72 |
+
|
| 73 |
output = BytesIO()
|
| 74 |
with pd.ExcelWriter(output, engine='openpyxl') as writer:
|
| 75 |
+
styled_df.to_excel(writer, index=False, sheet_name="Changed Repeats")
|
| 76 |
output.seek(0)
|
| 77 |
|
| 78 |
st.success("β
Comparison complete. Showing only changed repeats.")
|
| 79 |
st.download_button(
|
| 80 |
label="π₯ Download Excel",
|
| 81 |
data=output,
|
| 82 |
+
file_name="changed_repeats_with_percentage.xlsx",
|
| 83 |
mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
|
| 84 |
)
|
| 85 |
else:
|