Create app.py

app.py

@@ -0,0 +1,36 @@
+import streamlit as st
+import pandas as pd
+from pandas_profiling import ProfileReport
+
+st.set_page_config(page_title="File Upload and Profiling", layout="wide")
+
+st.title("File Upload and Profiling")
+
+uploaded_file = st.file_uploader("Upload a CSV file", type="csv")
+
+if uploaded_file is not None:
+    # Load the data using pandas
+    df = pd.read_csv(uploaded_file)
+
+    # Generate the pandas profiling report
+    profile = ProfileReport(df, explorative=True)
+
+    # Display the pandas profiling report using streamlit
+    st.header("Data Profiling Report")
+    st.write(profile.to_html(), unsafe_allow_html=True)
+
+    # Display word statistics for each categorical string column
+    cat_cols = df.select_dtypes(include='object').columns
+    st.header("Word Statistics for Categorical Columns")
+    for col in cat_cols:
+        st.subheader(col)
+        word_count = df[col].str.split().apply(len).value_counts().sort_index()
+        st.bar_chart(word_count)
+
+    # Grouped count by each feature
+    num_cols = df.select_dtypes(include=['float', 'int']).columns
+    st.header("Grouped Count by Each Feature")
+    for col in num_cols:
+        st.subheader(col)
+        count_by_feature = df.groupby(col).size().reset_index(name='count')
+        st.bar_chart(count_by_feature)