upload app.py with model and load dataset

app.py

@@ -0,0 +1,49 @@
+import streamlit as st
+from streamlit_shap import st_shap
+import shap
+from datasets import load_dataset
+from sklearn.model_selection import train_test_split
+import lightgbm as lgb
+import numpy as np
+import pandas as pd
+
+
+@st.experimental_memo
+def load_data():
+    dataset = load_dataset("ttd22/house-price", streaming = True)
+    df = pd.DataFrame.from_dict(dataset["train"])
+    df = df.drop('Id', axis=1)
+    drop_columns = (df.isnull().sum().sort_values(ascending=False).loc[lambda x : x > .90*1460]).index.to_list()
+    df = df.drop(drop_columns, axis = 'columns', errors = 'ignore')
+    cols_with_missing_values = df.columns[df.isnull().sum() > 0]
+    # Iterate through each column with missing values
+    for col in cols_with_missing_values:
+        # Check if the column is numeric
+        if df[col].dtype in ['int64', 'float64']:
+            # Impute missing values with median
+            median = df[col].median()
+            df[col].fillna(median, inplace=True)
+        else:
+            # Impute missing values with mode
+            mode = df[col].mode()[0]
+            df[col].fillna(mode, inplace=True)
+    X, y = df.drop("SalePrice", axis=1), df["SalePrice"]
+    # Extract categoricals and their indices
+    cat_features = X.select_dtypes(exclude=np.number).columns.to_list()
+    cat_idx = [X.columns.get_loc(col) for col in cat_features]
+    # Convert cat_features to pd.Categorical dtype
+    for col in cat_features:
+        X[col] = pd.Categorical(X[col])
+    return X,y,cat_idx
+
+@st.experimental_memo
+def load_model(X, y, cat_idx):
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+    params = {'n_estimators': 569, 'num_leaves': 62, 'max_depth': 10, 'learning_rate': 0.010786783375710743, 'colsample_bytree': 0.5065493231651268, 'subsample': 0.7900705177300663, 'lambda_l1': 4.998785478697207, 'lambda_l2': 2.1857959934319657, 'min_child_weight': 11.187719709451862}
+    model = lgb.LGBMRegressor(**params)
+    model.fit(X_train, y_train, eval_set=[(X_test, y_test)], categorical_feature=cat_idx, verbose = False)
+    return model
+
+# train LightGBM model
+X,y,cat_idx = load_data()
+model = load_model(X, y, cat_idx)

requirements.txt

@@ -0,0 +1,8 @@
+streamlit
+streamlit_shap
+shap
+datasets
+sklearn
+lightgbm
+numpy
+pandas