matsammut commited on
Commit
e978718
·
verified ·
1 Parent(s): b832f73

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +4 -4
app.py CHANGED
@@ -13,9 +13,9 @@ from sklearn.decomposition import PCA
13
  def predict(age, workclass, education, marital_status, occupation, relationship, race, gender, capital_gain, capital_loss, hours_per_week, native_country):
14
  features = [age, workclass, education, marital_status, occupation, relationship, race, gender, capital_gain, capital_loss, hours_per_week, native_country]
15
  columns = [
16
- "age", "workclass", "education", "marital_status", "occupation",
17
- "relationship", "race", "gender", "capital_gain", "capital_loss",
18
- "hours_per_week", "native_country"]
19
  df = pd.DataFrame(index=features, columns=columns)
20
  fixed_features = cleaning_features(df)
21
  # prediction = model.predict(features)
@@ -36,7 +36,7 @@ def cleaning_features(data):
36
 
37
  # 2. Label encode gender and income
38
  data['gender'] = le.fit_transform(data['gender'])
39
- data['education-num'] = le.fit_transform(data['education'])
40
 
41
  # 3. One-hot encode race
42
  for N in columns_to_encode:
 
13
  def predict(age, workclass, education, marital_status, occupation, relationship, race, gender, capital_gain, capital_loss, hours_per_week, native_country):
14
  features = [age, workclass, education, marital_status, occupation, relationship, race, gender, capital_gain, capital_loss, hours_per_week, native_country]
15
  columns = [
16
+ "age", "workclass", "education-num", "marital_status", "occupation",
17
+ "relationship", "race", "gender", "capital-gain", "capital-loss",
18
+ "hours-per-week", "native-country"]
19
  df = pd.DataFrame(index=features, columns=columns)
20
  fixed_features = cleaning_features(df)
21
  # prediction = model.predict(features)
 
36
 
37
  # 2. Label encode gender and income
38
  data['gender'] = le.fit_transform(data['gender'])
39
+ data['education-num'] = le.fit_transform(data['education-num'])
40
 
41
  # 3. One-hot encode race
42
  for N in columns_to_encode: