explore dataframe filtering

appStore/target.py

@@ -16,6 +16,11 @@ from utils.config import get_classifier_params
 from io import BytesIO
 import xlsxwriter
 import plotly.express as px
+from pandas.api.types import (
+    is_categorical_dtype,
+    is_datetime64_any_dtype,
+    is_numeric_dtype,
+    is_object_dtype,)
 
 # Declare all the necessary variables
 classifier_identifier = 'target'
@@ -132,8 +137,12 @@ def target_display():
         #         st.write("\t Text: \t{}".format(hits.iloc[i]['text'].replace("\n", " ")))
         #     hits = hits.reset_index(drop =True)
             st.write('----------------')
-            st.write('Explore the data')
-            AgGrid(hits)
+
+
+            st.title("Auto Filter Dataframes in Streamlit")
+            st.dataframe(filter_dataframe(hits))
+            # st.write('Explore the data')
+            # AgGrid(hits)
             df_xlsx = to_excel(df,hits)
             
             with st.sidebar:
@@ -142,6 +151,96 @@ def target_display():
                             data=df_xlsx ,
                             file_name= os.path.splitext(os.path.basename(st.session_state['filename']))[0]+'.xlsx')
 
+# st.write(
+#     """This app accomodates the blog [here](https://blog.streamlit.io/auto-generate-a-dataframe-filtering-ui-in-streamlit-with-filter_dataframe/)
+#     and walks you through one example of how the Streamlit
+#     Data Science Team builds add-on functions to Streamlit.
+#     """
+# )
+
+
+def filter_dataframe(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Adds a UI on top of a dataframe to let viewers filter columns
+
+    Args:
+        df (pd.DataFrame): Original dataframe
+
+    Returns:
+        pd.DataFrame: Filtered dataframe
+    """
+    modify = st.checkbox("Add filters")
+
+    if not modify:
+        return df
+
+    df = df.copy()
+
+    # Try to convert datetimes into a standard format (datetime, no timezone)
+    # for col in df.columns:
+    #     if is_object_dtype(df[col]):
+    #         try:
+    #             df[col] = pd.to_datetime(df[col])
+    #         except Exception:
+    #             pass
+
+    #     if is_datetime64_any_dtype(df[col]):
+    #         df[col] = df[col].dt.tz_localize(None)
+
+    modification_container = st.container()
+
+    with modification_container:
+        to_filter_columns = st.multiselect("Filter dataframe on", df.columns)
+        for column in to_filter_columns:
+            left, right = st.columns((1, 20))
+            left.write("↳")
+            # Treat columns with < 10 unique values as categorical
+            if is_categorical_dtype(df[column]) or df[column].nunique() < 10:
+                user_cat_input = right.multiselect(
+                    f"Values for {column}",
+                    df[column].unique(),
+                    default=list(df[column].unique()),
+                )
+                df = df[df[column].isin(user_cat_input)]
+            elif is_numeric_dtype(df[column]):
+                _min = float(df[column].min())
+                _max = float(df[column].max())
+                step = (_max - _min) / 100
+                user_num_input = right.slider(
+                    f"Values for {column}",
+                    _min,
+                    _max,
+                    (_min, _max),
+                    step=step,
+                )
+                df = df[df[column].between(*user_num_input)]
+            # elif is_datetime64_any_dtype(df[column]):
+            #     user_date_input = right.date_input(
+            #         f"Values for {column}",
+            #         value=(
+            #             df[column].min(),
+            #             df[column].max(),
+            #         ),
+            #     )
+            #     if len(user_date_input) == 2:
+            #         user_date_input = tuple(map(pd.to_datetime, user_date_input))
+            #         start_date, end_date = user_date_input
+            #         df = df.loc[df[column].between(start_date, end_date)]
+            else:
+                user_text_input = right.text_input(
+                    f"Substring or regex in {column}",
+                )
+                if user_text_input:
+                    df = df[df[column].str.contains(user_text_input)]
+
+    return df
+
+
+# df = pd.read_csv(
+#     "https://raw.githubusercontent.com/mcnakhaee/palmerpenguins/master/palmerpenguins/data/penguins.csv"
+# )
+
+
         # else:
         #     st.info("🤔 No Targets found")
             # count_df = df['Target Label'].value_counts()