Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -11,7 +11,7 @@ def clean_df(df):
|
|
11 |
print(f"Original columns: {df.columns}")
|
12 |
|
13 |
# Ensure clean URLs from the second column
|
14 |
-
second_col = df.iloc[:,
|
15 |
|
16 |
if second_col.str.contains('http').any() or second_col.str.contains('www').any():
|
17 |
df["url"] = second_col # Already has full URLs
|
@@ -20,18 +20,18 @@ def clean_df(df):
|
|
20 |
df["url"] = "https://www.shl.com" + second_col.str.replace(r'^(?!/)', '/', regex=True)
|
21 |
|
22 |
# Map T/F to Yes/No for remote testing and adaptive support
|
23 |
-
df["remote_support"] = df.iloc[:,
|
24 |
-
df["adaptive_support"] = df.iloc[:,
|
25 |
|
26 |
# Handle test_type properly - convert string representation of list to actual list
|
27 |
-
df["test_type"] = df.iloc[:,
|
28 |
|
29 |
# Get description from column 7
|
30 |
-
df["description"] = df.iloc[:,
|
31 |
|
32 |
# Extract duration with error handling from column 10
|
33 |
df["duration"] = pd.to_numeric(
|
34 |
-
df.iloc[:,
|
35 |
errors='coerce'
|
36 |
)
|
37 |
|
|
|
11 |
print(f"Original columns: {df.columns}")
|
12 |
|
13 |
# Ensure clean URLs from the second column
|
14 |
+
second_col = df.iloc[:, 2].astype(str) # Pre-packaged Job Solutions column
|
15 |
|
16 |
if second_col.str.contains('http').any() or second_col.str.contains('www').any():
|
17 |
df["url"] = second_col # Already has full URLs
|
|
|
20 |
df["url"] = "https://www.shl.com" + second_col.str.replace(r'^(?!/)', '/', regex=True)
|
21 |
|
22 |
# Map T/F to Yes/No for remote testing and adaptive support
|
23 |
+
df["remote_support"] = df.iloc[:, 3].map(lambda x: "Yes" if x == "T" else "No")
|
24 |
+
df["adaptive_support"] = df.iloc[:, 4].map(lambda x: "Yes" if x == "T" else "No")
|
25 |
|
26 |
# Handle test_type properly - convert string representation of list to actual list
|
27 |
+
df["test_type"] = df.iloc[:, 5].apply(lambda x: eval(x) if isinstance(x, str) else x)
|
28 |
|
29 |
# Get description from column 7
|
30 |
+
df["description"] = df.iloc[:, 6]
|
31 |
|
32 |
# Extract duration with error handling from column 10
|
33 |
df["duration"] = pd.to_numeric(
|
34 |
+
df.iloc[:, 9].astype(str).str.extract(r'(\d+)')[0],
|
35 |
errors='coerce'
|
36 |
)
|
37 |
|