Upload 3 files

app (1).py

@@ -0,0 +1,144 @@
+# cancer_prediction_app.py
+
+import streamlit as st
+import pandas as pd
+import numpy as np
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import StandardScaler, OneHotEncoder
+from sklearn.impute import SimpleImputer
+from sklearn.compose import ColumnTransformer
+from sklearn.linear_model import LogisticRegression
+
+# -----------------------------
+# Backstory, Problem Statement, Applications
+# -----------------------------
+st.title("🧬 Cancer Prediction using Machine Learning")
+
+st.sidebar.title("About Project")
+
+st.sidebar.markdown("""
+**Backstory:**  
+Cancer remains a leading cause of death worldwide. Early prediction and detection play a crucial role in improving survival rates. As data availability has increased, machine learning provides powerful tools to help medical professionals make more accurate predictions.
+
+**Problem Statement:**  
+Develop a machine learning model that predicts the likelihood of cancer based on patient features. The goal is to assist healthcare providers in making better-informed diagnostic decisions.
+
+**Applications:**  
+- Early detection and screening support.
+- Prioritization of high-risk patients.
+- Resource allocation in healthcare systems.
+""")
+
+st.markdown("""
+This app allows you to manually input all patient features and receive a prediction indicating whether cancer is present or not. The model is built with a robust pipeline combining **imputation**, **scaling**, **encoding**, and **logistic regression**.
+""")
+
+# -----------------------------
+# Load Data
+# -----------------------------
+@st.cache_data
+def load_data():
+    data = pd.read_csv("cancer_prediction_data.csv")
+    return data
+
+data = load_data()
+
+st.subheader("Dataset Columns:")
+st.write(list(data.columns))
+
+# -----------------------------
+# Identify Target and Features
+# -----------------------------
+TARGET_COLUMN = "Cancer_Present"
+
+if TARGET_COLUMN not in data.columns:
+    st.error(f"❌ Target column '{TARGET_COLUMN}' not found. Please check dataset columns above.")
+    st.stop()
+
+X = data.drop(TARGET_COLUMN, axis=1)
+y = data[TARGET_COLUMN]
+
+# -----------------------------
+# Detect categorical and numeric columns
+# -----------------------------
+categorical_cols = X.select_dtypes(include=["object", "category"]).columns.tolist()
+numeric_cols = X.select_dtypes(include=["int64", "float64"]).columns.tolist()
+
+st.write("Categorical columns detected:", categorical_cols)
+st.write("Numeric columns detected:", numeric_cols)
+
+# -----------------------------
+# Preprocessing pipeline
+# -----------------------------
+numeric_pipeline = Pipeline([
+    ("imputer", SimpleImputer(strategy="mean")),
+    ("scaler", StandardScaler())
+])
+
+categorical_pipeline = Pipeline([
+    ("imputer", SimpleImputer(strategy="most_frequent")),
+    ("encoder", OneHotEncoder(handle_unknown="ignore"))
+])
+
+preprocessor = ColumnTransformer([
+    ("num", numeric_pipeline, numeric_cols),
+    ("cat", categorical_pipeline, categorical_cols)
+])
+
+pipeline = Pipeline([
+    ("preprocessor", preprocessor),
+    ("classifier", LogisticRegression(max_iter=1000))
+])
+
+# -----------------------------
+# Train the pipeline
+# -----------------------------
+pipeline.fit(X, y)
+
+# -----------------------------
+# Sidebar Inputs for Prediction
+# -----------------------------
+st.sidebar.header("Enter Patient Features")
+
+def user_input_features():
+    input_data = {}
+    # Numeric inputs
+    for col in numeric_cols:
+        val = st.sidebar.number_input(
+            f"{col}",
+            min_value=float(X[col].min()) if not pd.isna(X[col].min()) else 0.0,
+            max_value=float(X[col].max()) if not pd.isna(X[col].max()) else 1.0,
+            value=float(X[col].mean()) if not pd.isna(X[col].mean()) else 0.0
+        )
+        input_data[col] = val
+    # Categorical inputs
+    for col in categorical_cols:
+        val = st.sidebar.selectbox(
+            f"{col}",
+            options=sorted(X[col].dropna().unique())
+        )
+        input_data[col] = val
+    return pd.DataFrame([input_data])
+
+input_df = user_input_features()
+
+# -----------------------------
+# Make Prediction
+# -----------------------------
+if st.button("Predict"):
+    prediction = pipeline.predict(input_df)[0]
+    prediction_proba = pipeline.predict_proba(input_df)[0][1]
+
+    st.subheader("Prediction Result")
+
+    if prediction == 1:
+        st.error("⚠️ **Cancer is Present**")
+    else:
+        st.success("✅ **No Cancer**")
+
+# -----------------------------
+# Additional Info
+# -----------------------------
+
+
+

requirements (2).txt

@@ -0,0 +1,8 @@
+altair
+pandas
+streamlit
+streamlit_drawable_canvas
+joblib
+pillow
+opencv-python
+scikit-learn