|
import streamlit as st |
|
from datasets import load_dataset |
|
import pandas as pd |
|
|
|
|
|
dataset = load_dataset("Langame/starter2") |
|
|
|
conversation_starters = [] |
|
for i in range(len(dataset["train"])): |
|
conversation_starters.append({ |
|
"conversation_starter": dataset["train"][i]["content"], |
|
"topics": dataset["train"][i]["topics"] |
|
}) |
|
|
|
df = pd.DataFrame(conversation_starters) |
|
|
|
from pandas.api.types import ( |
|
is_categorical_dtype, |
|
is_datetime64_any_dtype, |
|
is_numeric_dtype, |
|
is_object_dtype, |
|
) |
|
|
|
st.title("Conversation starters") |
|
|
|
st.write( |
|
"""Quick hack to search conversation starters for your next conversations in https://huggingface.co/datasets/Langame/starter2 |
|
""" |
|
) |
|
|
|
|
|
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() |
|
|
|
|
|
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("↳") |
|
|
|
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 |
|
|
|
|
|
st.dataframe(filter_dataframe(df)) |
|
|
