radwaamr1 commited on
Commit
ffccef2
·
verified ·
1 Parent(s): 20461ef

Upload app.py

Browse files
Files changed (1) hide show
  1. app.py +13 -24
app.py CHANGED
@@ -1,4 +1,5 @@
1
  # app.py
 
2
  import gradio as gr
3
  import pandas as pd
4
  import joblib
@@ -6,16 +7,8 @@ import numpy as np
6
  from sklearn.base import BaseEstimator, TransformerMixin
7
 
8
  # -------------------------------
9
- # Load saved artifacts
10
- # -------------------------------
11
- xgb_pipe = joblib.load("xgb_desertification_pipeline.pkl")
12
- le = joblib.load("label_encoder.pkl")
13
- expected_features = joblib.load("feature_names.pkl")
14
-
15
- # -------------------------------
16
- # FeatureFilter class
17
  # -------------------------------
18
- # Needed in case it's part of the pipeline
19
  class FeatureFilter(BaseEstimator, TransformerMixin):
20
  def __init__(self, expected_features):
21
  self.expected_features = expected_features
@@ -33,14 +26,19 @@ class FeatureFilter(BaseEstimator, TransformerMixin):
33
  X[c] = np.nan
34
  return X[self.expected_features]
35
 
 
 
 
 
 
 
 
36
  # -------------------------------
37
  # Prediction function
38
  # -------------------------------
39
  def predict_desertification(**kwargs):
40
- # Convert inputs to DataFrame
41
  df = pd.DataFrame([kwargs])
42
- df = df[expected_features] # reorder columns to match training
43
- # Predict
44
  pred_encoded = xgb_pipe.predict(df)
45
  pred_label = le.inverse_transform(pred_encoded)
46
  pred_proba = xgb_pipe.predict_proba(df).max(axis=1)
@@ -50,24 +48,15 @@ def predict_desertification(**kwargs):
50
  }
51
 
52
  # -------------------------------
53
- # Define Gradio interface
54
  # -------------------------------
55
- # Separate categorical and numeric inputs if needed
56
- inputs = []
57
- for feat in expected_features:
58
- if feat == "lc_type1":
59
- inputs.append(gr.Number(label=feat, value=0))
60
- else:
61
- inputs.append(gr.Number(label=feat, value=0.0))
62
 
63
- # Gradio app
64
  demo = gr.Interface(
65
  fn=predict_desertification,
66
  inputs=inputs,
67
  outputs="json",
68
- title="Desertification Level Predictor",
69
- description="Predict desertification level given soil, climate, and land cover features."
70
  )
71
 
72
- # Launch
73
  demo.launch()
 
1
  # app.py
2
+
3
  import gradio as gr
4
  import pandas as pd
5
  import joblib
 
7
  from sklearn.base import BaseEstimator, TransformerMixin
8
 
9
  # -------------------------------
10
+ # Define custom class BEFORE loading
 
 
 
 
 
 
 
11
  # -------------------------------
 
12
  class FeatureFilter(BaseEstimator, TransformerMixin):
13
  def __init__(self, expected_features):
14
  self.expected_features = expected_features
 
26
  X[c] = np.nan
27
  return X[self.expected_features]
28
 
29
+ # -------------------------------
30
+ # Load artifacts
31
+ # -------------------------------
32
+ xgb_pipe = joblib.load("xgb_desertification_pipeline.pkl")
33
+ le = joblib.load("label_encoder.pkl")
34
+ expected_features = joblib.load("feature_names.pkl")
35
+
36
  # -------------------------------
37
  # Prediction function
38
  # -------------------------------
39
  def predict_desertification(**kwargs):
 
40
  df = pd.DataFrame([kwargs])
41
+ df = df[expected_features] # reorder columns
 
42
  pred_encoded = xgb_pipe.predict(df)
43
  pred_label = le.inverse_transform(pred_encoded)
44
  pred_proba = xgb_pipe.predict_proba(df).max(axis=1)
 
48
  }
49
 
50
  # -------------------------------
51
+ # Gradio interface
52
  # -------------------------------
53
+ inputs = [gr.Number(label=f, value=0.0) for f in expected_features]
 
 
 
 
 
 
54
 
 
55
  demo = gr.Interface(
56
  fn=predict_desertification,
57
  inputs=inputs,
58
  outputs="json",
59
+ title="Desertification Level Predictor"
 
60
  )
61
 
 
62
  demo.launch()