Spaces:
Sleeping
Sleeping
Update cancer.py
Browse files
cancer.py
CHANGED
|
@@ -22,22 +22,25 @@ def preprocess_data(df):
|
|
| 22 |
nominal = ['Gender', 'Family_History', 'Smoking_History']
|
| 23 |
|
| 24 |
# Separate preprocessing steps for numeric and categorical features
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
preprocess = ColumnTransformer([
|
| 26 |
('num', Pipeline([
|
| 27 |
-
('imputer', SimpleImputer(strategy='mean')),
|
| 28 |
-
('scaler', StandardScaler())
|
| 29 |
]), numeric),
|
| 30 |
-
|
| 31 |
('ord', Pipeline([
|
| 32 |
-
('imputer', SimpleImputer(strategy='most_frequent')),
|
| 33 |
-
('encoder', OrdinalEncoder())
|
| 34 |
]), ordinal),
|
| 35 |
-
|
| 36 |
('nom', Pipeline([
|
| 37 |
-
('imputer', SimpleImputer(strategy='most_frequent')),
|
| 38 |
-
('encoder', OneHotEncoder(sparse_output=False, handle_unknown='ignore'))
|
| 39 |
]), nominal)
|
| 40 |
-
], remainder='passthrough')
|
| 41 |
|
| 42 |
X = df.drop('Cancer_Present', axis=1)
|
| 43 |
y = df['Cancer_Present']
|
|
@@ -75,7 +78,7 @@ with st.sidebar:
|
|
| 75 |
st.session_state['X_train'] = X_train
|
| 76 |
st.success(f"Model Trained Successfully! Accuracy: {accuracy:.2f}")
|
| 77 |
|
| 78 |
-
st.title("🎗️ Cancer Prediction
|
| 79 |
|
| 80 |
st.markdown("""<style>.big-font {font-size:20px !important;}</style>
|
| 81 |
<p class="big-font">Provide patient details below to predict cancer presence:</p>""", unsafe_allow_html=True)
|
|
|
|
| 22 |
nominal = ['Gender', 'Family_History', 'Smoking_History']
|
| 23 |
|
| 24 |
# Separate preprocessing steps for numeric and categorical features
|
| 25 |
+
def preprocess_data(df):
|
| 26 |
+
numeric = ['Age', 'Tumor_Size']
|
| 27 |
+
ordinal = ['Tumor_Grade', 'Symptoms_Severity', 'Alcohol_Consumption', 'Exercise_Frequency']
|
| 28 |
+
nominal = ['Gender', 'Family_History', 'Smoking_History']
|
| 29 |
+
# Data Preprocessing
|
| 30 |
preprocess = ColumnTransformer([
|
| 31 |
('num', Pipeline([
|
| 32 |
+
('imputer', SimpleImputer(strategy='mean')),
|
| 33 |
+
('scaler', StandardScaler())
|
| 34 |
]), numeric),
|
|
|
|
| 35 |
('ord', Pipeline([
|
| 36 |
+
('imputer', SimpleImputer(strategy='most_frequent')),
|
| 37 |
+
('encoder', OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=-1))
|
| 38 |
]), ordinal),
|
|
|
|
| 39 |
('nom', Pipeline([
|
| 40 |
+
('imputer', SimpleImputer(strategy='most_frequent')),
|
| 41 |
+
('encoder', OneHotEncoder(sparse_output=False, handle_unknown='ignore'))
|
| 42 |
]), nominal)
|
| 43 |
+
], remainder='passthrough')
|
| 44 |
|
| 45 |
X = df.drop('Cancer_Present', axis=1)
|
| 46 |
y = df['Cancer_Present']
|
|
|
|
| 78 |
st.session_state['X_train'] = X_train
|
| 79 |
st.success(f"Model Trained Successfully! Accuracy: {accuracy:.2f}")
|
| 80 |
|
| 81 |
+
st.title("🎗️ Cancer Prediction")
|
| 82 |
|
| 83 |
st.markdown("""<style>.big-font {font-size:20px !important;}</style>
|
| 84 |
<p class="big-font">Provide patient details below to predict cancer presence:</p>""", unsafe_allow_html=True)
|