claudecode/AvianVisitors
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

linted plotly

Browse Source
This commit is contained in:
mcguirepr89
2022-06-24 09:15:59 -04:00
parent 3d991d6cab
commit 5a971cea41
1 changed files with 80 additions and 87 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/plotly_streamlit.py
+80 -87
View File
@@ -6,13 +6,11 @@ from numpy import ma
import plotly.graph_objects as go import plotly.graph_objects as go
from plotly.subplots import make_subplots from plotly.subplots import make_subplots
import plotly.io as pio import plotly.io as pio
from datetime import timedelta, datetime from datetime import timedelta
from pathlib import Path
import sqlite3 import sqlite3
from sqlite3 import Connection from sqlite3 import Connection
import plotly.express as px import plotly.express as px
from sklearn.preprocessing import normalize from sklearn.preprocessing import normalize
import time
pio.templates.default = "plotly_white" pio.templates.default = "plotly_white"
@@ -40,9 +38,8 @@ st.markdown("""
""", unsafe_allow_html=True) """, unsafe_allow_html=True)
@st.cache(hash_funcs={Connection: id}) @st.cache(hash_funcs={Connection: id})
#@st.cache(allow_output_mutation=True) # @st.cache(allow_output_mutation=True)
def get_connection(path: str): def get_connection(path: str):
return sqlite3.connect(path, check_same_thread=False) return sqlite3.connect(path, check_same_thread=False)
@@ -58,19 +55,18 @@ df2 = df.copy()
df2['DateTime'] = pd.to_datetime(df2['Date'] + " " + df2['Time']) df2['DateTime'] = pd.to_datetime(df2['Date'] + " " + df2['Time'])
df2 = df2.set_index('DateTime') df2 = df2.set_index('DateTime')
daily = st.sidebar.checkbox('Single Day View', help= 'Select if you want single day view, unselect for multi-day views') daily = st.sidebar.checkbox('Single Day View', help='Select if you want single day view, unselect for multi-day views')
if daily: if daily:
# Date as slider # Date as slider
Start_Date = pd.to_datetime(df2.index.min()).date() Start_Date = pd.to_datetime(df2.index.min()).date()
End_Date = pd.to_datetime(df2.index.max()).date() End_Date = pd.to_datetime(df2.index.max()).date()
# cols1, cols2 = st.columns((1, 1)) # cols1, cols2 = st.columns((1, 1))
end_date = st.sidebar.date_input('Date to View', end_date = st.sidebar.date_input('Date to View',
min_value = Start_Date, min_value=Start_Date,
max_value = End_Date, max_value=End_Date,
value=(End_Date), value=(End_Date),
help= 'Select date for single day view' help='Select date for single day view')
)
start_date = end_date start_date = end_date
else: else:
Start_Date = pd.to_datetime(df2.index.min()).date() Start_Date = pd.to_datetime(df2.index.min()).date()
@@ -78,11 +74,10 @@ else:
# cols1, cols2 = st.columns((1, 1)) # cols1, cols2 = st.columns((1, 1))
start_date, end_date = st.sidebar.slider('Date Range', start_date, end_date = st.sidebar.slider('Date Range',
min_value = Start_Date-timedelta(days=1), min_value=Start_Date-timedelta(days=1),
max_value = End_Date, max_value=End_Date,
value=(Start_Date, End_Date), value=(Start_Date, End_Date),
help= 'Select start and end date, if same date get a clockplot for a single day' help='Select start and end date, if same date get a clockplot for a single day')
)
# start_date, end_date = cols1.date_input( # start_date, end_date = cols1.date_input(
# "Date Input for Analysis - select Range for single specie analysis, select single date for daily view", # "Date Input for Analysis - select Range for single specie analysis, select single date for daily view",
@@ -93,12 +88,14 @@ else:
# start_date = datetime(2022 ,5 ,17).date() # start_date = datetime(2022 ,5 ,17).date()
# end_date = datetime(2022 ,5 ,17).date() # end_date = datetime(2022 ,5 ,17).date()
@st.cache() @st.cache()
def date_filter(df, start_date, end_date): def date_filter(df, start_date, end_date):
filt = (df2.index >= pd.Timestamp(start_date)) & (df2.index <= pd.Timestamp(end_date + timedelta(days=1))) filt = (df2.index >= pd.Timestamp(start_date)) & (df2.index <= pd.Timestamp(end_date + timedelta(days=1)))
df = df[filt] df = df[filt]
return(df) return(df)
df2 = date_filter(df2, start_date, end_date) df2 = date_filter(df2, start_date, end_date)
st.write('<style>div.row-widget.stRadio > div{flex-direction:row;justify-content: left;} </style>', st.write('<style>div.row-widget.stRadio > div{flex-direction:row;justify-content: left;} </style>',
@@ -112,7 +109,7 @@ st.write('<style>div.st-bf{flex-direction:column;} div.st-ag{font-weight:bold;pa
if start_date == end_date: if start_date == end_date:
resample_sel = st.sidebar.radio( resample_sel = st.sidebar.radio(
"Resample Resolution", "Resample Resolution",
('Raw', '15 minutes', 'Hourly'), index=1, help= 'Select resolution for single day - larger times run faster' ) ('Raw', '15 minutes', 'Hourly'), index=1, help='Select resolution for single day - larger times run faster')
resample_times = {'Raw': 'Raw', resample_times = {'Raw': 'Raw',
'1 minute': '1min', '1 minute': '1min',
@@ -124,7 +121,7 @@ if start_date == end_date:
else: else:
resample_sel = st.sidebar.radio( resample_sel = st.sidebar.radio(
"Resample Resolution", "Resample Resolution",
('Raw', '15 minutes', 'Hourly', 'DAILY'), index=1, help= 'Select resolution for species - DAILY provides time series') ('Raw', '15 minutes', 'Hourly', 'DAILY'), index=1, help='Select resolution for species - DAILY provides time series')
resample_times = {'Raw': 'Raw', resample_times = {'Raw': 'Raw',
'1 minute': '1min', '1 minute': '1min',
@@ -134,6 +131,7 @@ else:
} }
resample_time = resample_times[resample_sel] resample_time = resample_times[resample_sel]
@st.cache() @st.cache()
def time_resample(df, resample_time): def time_resample(df, resample_time):
if resample_time == 'Raw': if resample_time == 'Raw':
@@ -143,6 +141,8 @@ def time_resample(df, resample_time):
df_resample = df.resample(resample_time)['Com_Name'].aggregate('unique').explode() df_resample = df.resample(resample_time)['Com_Name'].aggregate('unique').explode()
return(df_resample) return(df_resample)
top_bird = df2['Com_Name'].mode()[0] top_bird = df2['Com_Name'].mode()[0]
df5 = time_resample(df2, resample_time) df5 = time_resample(df2, resample_time)
@@ -151,12 +151,12 @@ df5 = time_resample(df2, resample_time)
Specie_Count = df5.value_counts() Specie_Count = df5.value_counts()
# Create Hourly Crosstab # Create Hourly Crosstab
hourly = pd.crosstab(df5, df5.index.hour, dropna=True, margins= True) hourly = pd.crosstab(df5, df5.index.hour, dropna=True, margins=True)
# Filter on species # Filter on species
species = list(hourly.sort_values("All", ascending= False).index) species = list(hourly.sort_values("All", ascending=False).index)
#cols1, cols2 = st.columns((1, 1)) # cols1, cols2 = st.columns((1, 1))
top_N = st.sidebar.slider( top_N = st.sidebar.slider(
'Select Number of Birds to Show', 'Select Number of Birds to Show',
min_value=1, min_value=1,
@@ -168,26 +168,26 @@ top_N_species = (df5.value_counts()[:top_N])
font_size = 15 font_size = 15
if daily == False: if daily is False:
if resample_time != '1D': if resample_time != '1D':
specie = st.selectbox( specie = st.selectbox(
'Which bird would you like to explore for the dates ' 'Which bird would you like to explore for the dates '
+ str(start_date) + ' to ' + str(end_date) + '?', + str(start_date) + ' to ' + str(end_date) + '?',
species, species,
index = 0) index=0)
# filt = df2['Com_Name'] == specie # filt = df2['Com_Name'] == specie
if specie == 'All': if specie == 'All':
df_counts = int(hourly[hourly.index==specie]['All']) df_counts = int(hourly[hourly.index == specie]['All'])
fig = make_subplots( fig = make_subplots(
rows=3, cols=2, rows=3, cols=2,
specs=[[{"type": "xy", "rowspan": 3}, {"type": "polar", "rowspan": 2}], [{"rowspan": 1}, {"rowspan": 1}], specs=[[{"type": "xy", "rowspan": 3}, {"type": "polar", "rowspan": 2}],
[None, {"type": "xy", "rowspan": 1}]], [{"rowspan": 1}, {"rowspan": 1}],
[None, {"type": "xy", "rowspan": 1}]],
subplot_titles=('<b>Top ' + str(top_N) + ' Species in Date Range ' + str(start_date) + ' to ' + str( subplot_titles=('<b>Top ' + str(top_N) + ' Species in Date Range ' + str(start_date) + ' to ' + str(
end_date) + '<br>for ' + str(resample_sel) + ' sampling interval.' + '</b>', end_date) + '<br>for ' + str(resample_sel) + ' sampling interval.' + '</b>',
'Total Detect:' + str('{:,}'.format(df_counts)) 'Total Detect:' + str('{:,}'.format(df_counts))
# + ' Confidence Max:' + str( # + ' Confidence Max:' + str(
# '{:.2f}%'.format(max(df2[df2['Com_Name'] == specie]['Confidence']) * 100)) + # '{:.2f}%'.format(max(df2[df2['Com_Name'] == specie]['Confidence']) * 100)) +
# ' ' + ' Median:' + str( # ' ' + ' Median:' + str(
@@ -197,9 +197,9 @@ if daily == False:
fig.layout.annotations[1].update(x=0.7, y=0.25, font_size=15) fig.layout.annotations[1].update(x=0.7, y=0.25, font_size=15)
# Plot seen species for selected date range and number of species # Plot seen species for selected date range and number of species
fig.add_trace(go.Bar(y=top_N_species.index, x=top_N_species, orientation='h', marker_color='seagreen'), row=1, col=1) fig.add_trace(go.Bar(y=top_N_species.index, x=top_N_species, orientation='h', marker_color='seagreen'), row=1, col=1)
fig.update_layout( fig.update_layout(
margin=dict(l=0, r=0, t=50, b=0), margin=dict(l=0, r=0, t=50, b=0),
yaxis={'categoryorder': 'total ascending'}) yaxis={'categoryorder': 'total ascending'})
@@ -232,16 +232,17 @@ if daily == False:
rotation=-90, rotation=-90,
direction='clockwise', direction='clockwise',
tickmode='array', tickmode='array',
tickvals=[0, 15, 35, 45, 60, 75, 90, 105, 120, 135, 150, 165, 180, 195, 210, 225, 240, 255, 270, tickvals=[0, 15, 35, 45, 60, 75, 90, 105, 120, 135, 150, 165, 180, 195, 210,
285, 300, 315, 330, 345], 225, 240, 255, 270, 285, 300, 315, 330, 345],
ticktext=['12am', '1am', '2am', '3am', '4am', '5am', '6am', '7am', '8am', '9am', '10am', '11am', ticktext=['12am', '1am', '2am', '3am', '4am', '5am', '6am', '7am', '8am', '9am',
'12pm', '1pm', '2pm', '3pm', '4pm', '5pm', '6pm', '7pm', '8pm', '9pm', '10pm', '11pm'], '10am', '11am', '12pm', '1pm', '2pm', '3pm', '4pm', '5pm', '6pm',
'7pm', '8pm', '9pm', '10pm', '11pm'],
hoverformat="#%{theta}: <br>Popularity: %{percent} </br> %{r}" hoverformat="#%{theta}: <br>Popularity: %{percent} </br> %{r}"
), ),
), ),
) )
daily = pd.crosstab(df5, df5.index.date, dropna=True, margins = True) daily = pd.crosstab(df5, df5.index.date, dropna=True, margins=True)
fig.add_trace(go.Bar(x=daily.columns[:-1], y=daily.loc[specie][:-1], marker_color='seagreen'), row=3, col=2) fig.add_trace(go.Bar(x=daily.columns[:-1], y=daily.loc[specie][:-1], marker_color='seagreen'), row=3, col=2)
st.plotly_chart(fig, use_container_width=True) # , config=config) st.plotly_chart(fig, use_container_width=True) # , config=config)
@@ -250,7 +251,7 @@ if daily == False:
with col1: with col1:
fig = make_subplots( fig = make_subplots(
rows=3, cols=1, rows=3, cols=1,
specs=[[{"type": "polar", "rowspan": 2}],[{"rowspan": 1}], [{"type": "xy", "rowspan": 1}]] specs=[[{"type": "polar", "rowspan": 2}], [{"rowspan": 1}], [{"type": "xy", "rowspan": 1}]]
) )
# Set 360 degrees, 24 hours for polar plot # Set 360 degrees, 24 hours for polar plot
theta = np.linspace(0.0, 360, 24, endpoint=False) theta = np.linspace(0.0, 360, 24, endpoint=False)
@@ -280,81 +281,75 @@ if daily == False:
rotation=-90, rotation=-90,
direction='clockwise', direction='clockwise',
tickmode='array', tickmode='array',
tickvals=[0, 15, 35, 45, 60, 75, 90, 105, 120, 135, 150, 165, 180, 195, 210, 225, 240, 255, 270, tickvals=[0, 15, 35, 45, 60, 75, 90, 105, 120, 135, 150, 165, 180, 195,
285, 300, 315, 330, 345], 210, 225, 240, 255, 270, 285, 300, 315, 330, 345],
ticktext=['12am', '1am', '2am', '3am', '4am', '5am', '6am', '7am', '8am', '9am', '10am', '11am', ticktext=['12am', '1am', '2am', '3am', '4am', '5am', '6am', '7am', '8am',
'12pm', '1pm', '2pm', '3pm', '4pm', '5pm', '6pm', '7pm', '8pm', '9pm', '10pm', '11pm'], '9am', '10am', '11am', '12pm', '1pm', '2pm', '3pm', '4pm', '5pm',
'6pm', '7pm', '8pm', '9pm', '10pm', '11pm'],
hoverformat="#%{theta}: <br>Popularity: %{percent} </br> %{r}" hoverformat="#%{theta}: <br>Popularity: %{percent} </br> %{r}"
), ),
), ),
) )
daily = pd.crosstab(df5, df5.index.date, dropna=True, margins = True) daily = pd.crosstab(df5, df5.index.date, dropna=True, margins=True)
fig.add_trace(go.Bar(x=daily.columns[:-1], y=daily.loc[specie][:-1], marker_color='seagreen'), row=3, col=1) fig.add_trace(go.Bar(x=daily.columns[:-1], y=daily.loc[specie][:-1], marker_color='seagreen'), row=3, col=1)
st.plotly_chart(fig, use_container_width=True) # , config=config) st.plotly_chart(fig, use_container_width=True) # , config=config)
df_counts = int(hourly[hourly.index==specie]['All']) df_counts = int(hourly[hourly.index == specie]['All'])
st.subheader('Total Detect:' + str('{:,}'.format(df_counts)) st.subheader('Total Detect:' + str('{:,}'.format(df_counts))
+ ' Confidence Max:' + str( + ' Confidence Max:' +
'{:.2f}%'.format(max(df2[df2['Com_Name'] == specie]['Confidence']) * 100)) + str('{:.2f}%'.format(max(df2[df2['Com_Name'] == specie]['Confidence']) * 100))
' ' + ' Median:' + str( + ' ' + ' Median:' +
'{:.2f}%'.format(np.median(df2[df2['Com_Name'] == specie]['Confidence']) * 100))) str('{:.2f}%'.format(np.median(df2[df2['Com_Name'] == specie]['Confidence']) * 100)))
recordings = df2[df2['Com_Name'] == specie]['File_Name']
recordings=df2[df2['Com_Name']==specie]['File_Name']
with col2: with col2:
try: try:
recording = st.selectbox('Available recordings', recordings.sort_index(ascending=False)) recording = st.selectbox('Available recordings', recordings.sort_index(ascending=False))
date_specie = df2.loc[df2['File_Name']==recording,['Date','Com_Name']] date_specie = df2.loc[df2['File_Name'] == recording, ['Date', 'Com_Name']]
date_dir = date_specie['Date'].values[0] date_dir = date_specie['Date'].values[0]
specie_dir = date_specie['Com_Name'].values[0].replace(" ","_") specie_dir = date_specie['Com_Name'].values[0].replace(" ", "_")
st.image(userDir + '/BirdSongs/Extracted/By_Date/'+ date_dir + '/'+ specie_dir + '/' + recording + '.png') st.image(userDir + '/BirdSongs/Extracted/By_Date/' + date_dir + '/' + specie_dir + '/' + recording + '.png')
st.audio(userDir +'/BirdSongs/Extracted/By_Date/'+ date_dir + '/'+ specie_dir + '/' + recording) st.audio(userDir + '/BirdSongs/Extracted/By_Date/' + date_dir + '/' + specie_dir + '/' + recording)
except: except Exception:
st.title('RECORDING NOT AVAILABLE :(') st.title('RECORDING NOT AVAILABLE :(')
# try: # try:
# con = sqlite3.connect(userDir + '/BirdNET-Pi/scripts/birds.db') # con = sqlite3.connect(userDir + '/BirdNET-Pi/scripts/birds.db')
# cur = con.cursor() # cur = con.cursor()
cola, colb, colc, cold = st.columns((3,1,1,1)) cola, colb, colc, cold = st.columns((3, 1, 1, 1))
with colb: with colb:
seen = st.checkbox('Reviewed') seen = st.checkbox('Reviewed')
if seen: if seen:
with colc: with colc:
verified = st.radio("Verification",['True Positive','False Positive']) verified = st.radio("Verification", ['True Positive', 'False Positive'])
if verified == "False Positive": if verified == "False Positive":
df_names = pd.read_csv(userDir+'/BirdNET-Pi/model/labels.txt', delimiter= '_', names=['Sci_Name', 'Com_Name']) df_names = pd.read_csv(userDir + '/BirdNET-Pi/model/labels.txt', delimiter='_', names=['Sci_Name', 'Com_Name'])
df_unknown= pd.DataFrame({"Sci_Name":["UNKNOWN"],"Com_Name":["UNKNOWN"]}) df_unknown = pd.DataFrame({"Sci_Name": ["UNKNOWN"], "Com_Name": ["UNKNOWN"]})
df_names = pd.concat([df_unknown,df_names], ignore_index=True) df_names = pd.concat([df_unknown, df_names], ignore_index=True)
with cold: with cold:
corrected = st.selectbox('What species?', df_names['Com_Name']) corrected = st.selectbox('What species?', df_names['Com_Name'])
# cur.execute("UPDATE detections SET Seen = seen WHERE File_Name = recording") # cur.execute("UPDATE detections SET Seen = seen WHERE File_Name = recording")
# con.commit() # con.commit()
# con.close() # con.close()
# except BaseException: # except BaseException:
# print("Database busy") # print("Database busy")
# time.sleep(2) # time.sleep(2)
else: else:
specie = st.selectbox( specie = st.selectbox('Which bird would you like to explore for the dates '
'Which bird would you like to explore for the dates ' + str(start_date) + ' to ' + str(end_date) + '?',
+ str(start_date) + ' to ' + str(end_date) + '?', species[1:],
species[1:], index=0)
index = 0)
# filt = df2[df2['Com_Name'] == specie] # filt = df2[df2['Com_Name'] == specie]
df_counts = int(hourly[hourly.index==specie]['All']) df_counts = int(hourly[hourly.index == specie]['All'])
fig = st.container() fig = st.container()
fig = make_subplots( fig = make_subplots(rows=1, cols=1)
rows=1, cols =1)
# specs= [[{"type":"xy","rowspan":1},{"type":"heatmap","rowspan":1}]], # specs= [[{"type":"xy","rowspan":1},{"type":"heatmap","rowspan":1}]],
# subplot_titles=('<b>Daily Top '+ str(top_N) + ' Species in Date Range '+ str(start_date) +' to '+ str(end_date) +'</b>', # subplot_titles=('<b>Daily Top '+ str(top_N) + ' Species in Date Range '+ str(start_date) +' to '+ str(end_date) +'</b>',
# '<b>Daily ' + specie+ ' Detections on 15 minute intervals </b>'), # '<b>Daily ' + specie+ ' Detections on 15 minute intervals </b>'),
@@ -365,9 +360,9 @@ if daily == False:
# ) # )
# fig.add_trace(go.Bar(y=top_N_species.index, x=top_N_species, orientation='h'), row=1,col=1) # fig.add_trace(go.Bar(y=top_N_species.index, x=top_N_species, orientation='h'), row=1,col=1)
df4=df2['Com_Name'][df2['Com_Name']==specie].resample('15min').count() df4 = df2['Com_Name'][df2['Com_Name'] == specie].resample('15min').count()
df4.index=[df4.index.date, df4.index.time] df4.index = [df4.index.date, df4.index.time]
day_hour_freq=df4.unstack().fillna(0) day_hour_freq = df4.unstack().fillna(0)
fig_x = [d.strftime('%d-%m-%Y') for d in day_hour_freq.index.tolist()] fig_x = [d.strftime('%d-%m-%Y') for d in day_hour_freq.index.tolist()]
fig_y = [h.strftime('%H:%M') for h in day_hour_freq.columns.tolist()] fig_y = [h.strftime('%H:%M') for h in day_hour_freq.columns.tolist()]
@@ -377,9 +372,9 @@ if daily == False:
# fig.update_layout( # fig.update_layout(
# margin=dict(l=0, r=0, t=50, b=0), # margin=dict(l=0, r=0, t=50, b=0),
# yaxis={'categoryorder':'total ascending'}) # yaxis={'categoryorder':'total ascending'})
color_pals= px.colors.named_colorscales() color_pals = px.colors.named_colorscales()
selected_pal = st.sidebar.selectbox('Select Color Pallet for Daily Detections', color_pals) selected_pal = st.sidebar.selectbox('Select Color Pallet for Daily Detections', color_pals)
fig.add_trace(go.Heatmap(x=fig_x,y=fig_y,z=fig_z, autocolorscale = False, colorscale = selected_pal), row=1, col=1) fig.add_trace(go.Heatmap(x=fig_x, y=fig_y, z=fig_z, autocolorscale=False, colorscale=selected_pal), row=1, col=1)
st.plotly_chart(fig, use_container_width=True) # , config=config) st.plotly_chart(fig, use_container_width=True) # , config=config)
else: else:
fig = make_subplots( fig = make_subplots(
@@ -436,9 +431,7 @@ else:
st.plotly_chart(fig, use_container_width=True) # , config=config) st.plotly_chart(fig, use_container_width=True) # , config=config)
# cols3,cols4=st.columns((1,1)) # cols3,cols4=st.columns((1,1))
#
# extract_date=Date_Slider # extract_date=Date_Slider
#
# audio_file = open('/home/*/BirdSongs/Extracted/By_Date/2022-03-22/Yellow-streaked_Greenbul/Yellow-streaked_Greenbul-77-2022-03-22-birdnet-15:04:28.mp3', 'rb') # audio_file = open('/home/*/BirdSongs/Extracted/By_Date/2022-03-22/Yellow-streaked_Greenbul/Yellow-streaked_Greenbul-77-2022-03-22-birdnet-15:04:28.mp3', 'rb')
# audio_bytes = audio_file.read() # audio_bytes = audio_file.read()
# cols4.audio(audio_bytes, format='audio/mp3') # cols4.audio(audio_bytes, format='audio/mp3')