Upload app (1).py

app (1).py

@@ -0,0 +1,113 @@
+import streamlit as st
+import pandas as pd
+import io
+import base64
+from sklearn.impute import SimpleImputer
+
+
+st.set_page_config(page_title="CSV Data Cleaning Tool")
+
+hide_streamlit_style = """
+            <style>
+            #MainMenu {visibility: hidden;}
+            footer {visibility: hidden;}
+            </style>
+            """
+st.markdown(hide_streamlit_style, unsafe_allow_html=True)
+
+st.title("CSV Data Tool")
+
+st.markdown("กดเลือกหัว Tool ข้อที่ต้องการจะใช้ได้เลยนะจ๊ะ")
+
+uploaded_files = st.file_uploader("Choose CSV files", type="csv", accept_multiple_files=True)
+
+dataframes = []
+
+if uploaded_files:
+    for file in uploaded_files:
+        file.seek(0)
+        df = pd.read_csv(file)
+        dataframes.append(df)
+
+    st.markdown("Data Cleansing")
+
+    duplicate_columns = st.checkbox("Remove duplicate columns", value=False)
+    if duplicate_columns :
+        for i, df in enumerate(dataframes):
+            dataframes[i] = df.drop_duplicates(inplace=False)
+    
+    remove_empty_rows = st.checkbox("Remove empty rows", value=False)
+    if remove_empty_rows:
+        for i, df in enumerate(dataframes):
+            dataframes[i] = df.dropna(how="all", inplace=False)
+    
+    impute_mean = st.checkbox("Impute missing values with mean (for int and float columns)",value=False)
+    if impute_mean:
+        for i, df in enumerate(dataframes):
+            numeric_cols = df.select_dtypes(include=['int', 'float']).columns
+            imputer = SimpleImputer(strategy='mean')
+            df[numeric_cols] = imputer.fit_transform(df[numeric_cols])
+            dataframes[i] = df                       
+
+    impute_most_frequent = st.checkbox("Impute missing values with most frequent category (for categorical columns)",value=False)
+    if impute_most_frequent:
+        for i, df in enumerate(dataframes):
+            categorical_cols = df.select_dtypes(include=['object']).columns
+            imputer = SimpleImputer(strategy='most_frequent')
+            df[categorical_cols] = imputer.fit_transform(df[categorical_cols])
+            dataframes[i] = df
+
+    
+    selected_out = st.selectbox("เลือก columns ที่จะดู Outlier", df.columns)
+    if selected_out:
+        col = selected_out
+        st.write(f"คอลัมน์ {col}:")
+        # Calculate Z-Scores for the selected column
+        z_scores = np.abs((df[col] - df[col].mean()) / df[col].std())
+        # Set a threshold for identifying outliers (e.g., z_score > 3)
+        threshold = 3
+        # Identify outliers
+        outliers = df[z_scores > threshold]
+        st.write("Outliers:")
+        st.write(outliers)
+
+    
+    st.markdown("Data transform")
+    
+    for i, df in enumerate(dataframes):
+        st.dataframe(df)
+    
+    selected_values = st.multiselect("เลือกค่าจากคอลัมน์", df.columns)
+
+    
+    convert_to_String = st.checkbox("convert columns to String", value=False)
+    convert_to_float = st.checkbox("convert columns to Float", value=False)
+    if convert_to_String:
+        df[selected_values] = df[selected_values].astype(str)
+    if convert_to_float:
+        df[selected_values] = df[selected_values].astype(float)
+
+    
+    
+
+    
+    show_dataframes = st.checkbox("Show DataFrames", value=True)
+    if show_dataframes:
+        for i, df in enumerate(dataframes):
+            st.write(f"DataFrame {i + 1}")
+            st.dataframe(df)
+            
+
+    
+if st.button("Download cleaned data"):
+    for i, df in enumerate(dataframes):
+        csv = df.to_csv(index=False)
+        b64 = base64.b64encode(csv.encode()).decode()
+        href = f'<a href="data:file/csv;base64,{b64}" download="cleaned_data_{i + 1}.csv">Download cleaned_data_{i + 1}.csv</a>'
+        st.markdown(href, unsafe_allow_html=True)
+
+
+st.markdown("")
+st.markdown("---")
+st.markdown("")
+