varshitha22 commited on
Commit
96de38d
·
verified ·
1 Parent(s): f3ceff8

Update cancer.py

Browse files
Files changed (1) hide show
  1. cancer.py +11 -13
cancer.py CHANGED
@@ -23,18 +23,20 @@ def preprocess_data(df):
23
 
24
  preprocess = ColumnTransformer([
25
  ('num', Pipeline([
26
- ('imputer', SimpleImputer(strategy='mean')),
27
- ('scaler', StandardScaler())
28
  ]), numeric),
 
29
  ('ord', Pipeline([
30
- ('imputer', SimpleImputer(strategy='most_frequent')),
31
- ('encoder', OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=-1))
32
  ]), ordinal),
 
33
  ('nom', Pipeline([
34
- ('imputer', SimpleImputer(strategy='most_frequent')),
35
- ('encoder', OneHotEncoder(sparse_output=False, handle_unknown='ignore'))
36
  ]), nominal)
37
- ], remainder='passthrough')
38
 
39
  X = df.drop('Cancer_Present', axis=1)
40
  y = df['Cancer_Present']
@@ -72,7 +74,7 @@ with st.sidebar:
72
  st.session_state['X_train'] = X_train
73
  st.success(f"Model Trained Successfully! Accuracy: {accuracy:.2f}")
74
 
75
- st.title("🎗️ Cancer Prediction")
76
 
77
  st.markdown("""<style>.big-font {font-size:20px !important;}</style>
78
  <p class="big-font">Provide patient details below to predict cancer presence:</p>""", unsafe_allow_html=True)
@@ -88,7 +90,7 @@ with col2:
88
  smoking_history = st.selectbox("Smoking History", ['Never Smoker', 'Former Smoker', 'Current Smoker'])
89
  alcohol_consumption = st.selectbox("Alcohol Consumption", ['Low','Moderate','High'])
90
  exercise_frequency = st.selectbox("Exercise Frequency", ['Rarely', 'Occasionally', 'Regularly','Never'])
91
- gender = st.selectbox("Gender", ['Male', "Female"])
92
  family_history = st.selectbox("Family History", ["No", "Yes"])
93
 
94
  input_data = [[age, tumor_size, tumor_grade, symptoms_severity, smoking_history,
@@ -98,8 +100,6 @@ if st.button("Predict Cancer Presence"):
98
  if 'trained_model' in st.session_state:
99
  model = st.session_state['trained_model']
100
  X_train = st.session_state['X_train']
101
-
102
- # Reorder input_data columns to match X_train columns
103
  input_df = pd.DataFrame(input_data, columns=X_train.columns)
104
  input_transformed = model.named_steps['preprocessor'].transform(input_df)
105
  prediction = model.named_steps['classifier'].predict(input_transformed)
@@ -112,5 +112,3 @@ if st.button("Predict Cancer Presence"):
112
  st.write("Good news! The model predicts that there is no cancer detected. Stay healthy!")
113
  else:
114
  st.error("Please train a model first!")
115
-
116
-
 
23
 
24
  preprocess = ColumnTransformer([
25
  ('num', Pipeline([
26
+ ('imputer', SimpleImputer(strategy='mean')), # Impute numeric columns with the mean
27
+ ('scaler', StandardScaler()) # Standardize numeric columns
28
  ]), numeric),
29
+
30
  ('ord', Pipeline([
31
+ ('imputer', SimpleImputer(strategy='most_frequent')), # Impute ordinal columns with the most frequent value
32
+ ('encoder', OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=-1)) # Encode ordinal columns
33
  ]), ordinal),
34
+
35
  ('nom', Pipeline([
36
+ ('imputer', SimpleImputer(strategy='most_frequent')), # Impute nominal columns with the most frequent value
37
+ ('encoder', OneHotEncoder(sparse_output=False, handle_unknown='ignore')) # One hot encode nominal columns
38
  ]), nominal)
39
+ ], remainder='passthrough') # Keep other columns unchanged
40
 
41
  X = df.drop('Cancer_Present', axis=1)
42
  y = df['Cancer_Present']
 
74
  st.session_state['X_train'] = X_train
75
  st.success(f"Model Trained Successfully! Accuracy: {accuracy:.2f}")
76
 
77
+ st.title("🎗️ Cancer Prediction Using Machine Learning 🎗️")
78
 
79
  st.markdown("""<style>.big-font {font-size:20px !important;}</style>
80
  <p class="big-font">Provide patient details below to predict cancer presence:</p>""", unsafe_allow_html=True)
 
90
  smoking_history = st.selectbox("Smoking History", ['Never Smoker', 'Former Smoker', 'Current Smoker'])
91
  alcohol_consumption = st.selectbox("Alcohol Consumption", ['Low','Moderate','High'])
92
  exercise_frequency = st.selectbox("Exercise Frequency", ['Rarely', 'Occasionally', 'Regularly','Never'])
93
+ gender = st.selectbox("Gender", [0, 1])
94
  family_history = st.selectbox("Family History", ["No", "Yes"])
95
 
96
  input_data = [[age, tumor_size, tumor_grade, symptoms_severity, smoking_history,
 
100
  if 'trained_model' in st.session_state:
101
  model = st.session_state['trained_model']
102
  X_train = st.session_state['X_train']
 
 
103
  input_df = pd.DataFrame(input_data, columns=X_train.columns)
104
  input_transformed = model.named_steps['preprocessor'].transform(input_df)
105
  prediction = model.named_steps['classifier'].predict(input_transformed)
 
112
  st.write("Good news! The model predicts that there is no cancer detected. Stay healthy!")
113
  else:
114
  st.error("Please train a model first!")