Create app.py

app.py

@@ -0,0 +1,60 @@
+import streamlit as st
+import pandas as pd
+from pandas_profiling import ProfileReport
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression
+from sklearn.tree import DecisionTreeRegressor
+from sklearn.ensemble import RandomForestRegressor
+import plotly.express as px
+
+# Data Ingestion
+uploaded_file = st.file_uploader("Upload your dataset:", type=["csv",_"xlsx",_"json"])
+if uploaded_file:
+    df = pd.read_csv(uploaded_file)
+    st.write("Data Preview:")
+    st.write(df.head())
+
+# Data Preparation
+st.write("Data Preparation:")
+profile = ProfileReport(df, title="Data Profiling Report")
+st.write(profile)
+
+# Data Cleaning
+st.write("Data Cleaning:")
+handle_missing_values = st.selectbox("Handle missing values:", ["Mean",_"Median",_"Imputation"])
+handle_outliers = st.selectbox("Handle outliers:", ["Standardization",_"_Winsorization"])
+
+# Model Training
+st.write("Model Training:")
+model_type = st.selectbox("Choose a model:", ["Linear_Regression",_"Decision_Trees",_"Random_Forest"])
+hyperparams = {}
+if model_type == "Linear Regression":
+    hyperparams["alpha"] = st.slider("Regularization strength:", 0.1, 10.0)
+elif model_type == "Decision Trees":
+    hyperparams["max_depth"] = st.slider("Maximum depth:", 1, 10)
+elif model_type == "Random Forest":
+    hyperparams["n_estimators"] = st.slider("Number of estimators:", 10, 100)
+
+X_train, X_test, y_train, y_test = train_test_split(df.drop("target", axis=1), df["target"], test_size=0.2, random_state=42)
+
+if model_type == "Linear Regression":
+    model = LinearRegression(**hyperparams)
+elif model_type == "Decision Trees":
+    model = DecisionTreeRegressor(**hyperparams)
+elif model_type == "Random Forest":
+    model = RandomForestRegressor(**hyperparams)
+
+model.fit(X_train, y_train)
+y_pred = model.predict(X_test)
+
+# Model Evaluation
+st.write("Model Evaluation:")
+st.write("Accuracy:", model.score(X_test, y_test))
+st.write("Confusion Matrix:")
+conf_mat = pd.crosstab(y_test, y_pred, rownames=["Actual"], colnames=["Predicted"])
+st.plotly(px.imshow(conf_mat, color_continuous_scale="blues"), use_container_width=True)
+
+# Model Deployment
+st.write("Model Deployment:")
+download_model = st.download_button("Download trained model", data=model, file_name="model.py")
+deploy_to_cloud = st.button("Deploy to cloud platform")