Spaces:
Running
Running
File size: 1,424 Bytes
41c5156 a4eb606 41c5156 a4eb606 41c5156 a4eb606 41c5156 a4eb606 41c5156 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
import streamlit as st
import pandas as pd
from dataset.cleaner import clean_lat_long, clean_date
from dataset.download import get_dataset
from dataset.fake_data import generate_fake_data
def data_prep():
"Doing data prep"
df = get_dataset()
# df = generate_fake_data(df, 100)
df = clean_lat_long(df)
df = clean_date(df)
return df
def filter_data(df):
df_filtered = df[
(df['date'] >= pd.to_datetime(st.session_state.date_range[0])) &
(df['date'] <= pd.to_datetime(st.session_state.date_range[1])) &
(df['lon'] >= st.session_state.lon_range[0]) &
(df['lon'] <= st.session_state.lon_range[1]) &
(df['lat'] >= st.session_state.lat_range[0]) &
(df['lat'] <= st.session_state.lat_range[1])
]
return df_filtered
def show_specie_author(df):
print(df)
df = df.groupby(['species', 'author_email']).size().reset_index(name='counts')
for specie in df["species"].unique():
st.subheader(f"Species: {specie}")
specie_data = df[df['species'] == specie]
for _, row in specie_data.iterrows():
key = f"{specie}_{row['author_email']}"
label = f"{row['author_email']} ({row['counts']})"
st.session_state.checkbox_states[key] = st.checkbox(label, key=key)
def show_new_data_view(df):
df = filter_data(df)
df_ordered = show_specie_author(df)
return df_ordered
|