Update app.py

webapp/app.py

@@ -3,4 +3,181 @@ import pandas as pd
 st.write("""
 # My first app
 Hello *world!*
-""")
\ No newline at end of file
+""")
+import numpy as np
+import matplotlib.pyplot as plt
+import pyvo as vo
+import pandas as pd
+import matplotlib as mpl
+
+
+@st.cache
+def get_data_sql():    
+    # init tap service
+    tap_service = vo.dal.TAPService('https://gaia.aip.de/tap')
+    #vo.utils.http.session.headers['Authorization'] = 'Your Token '
+    
+    # manage the jobs yourself
+    jobs = []
+    
+    limit = 100000
+    total = 200000
+    qstr="select  source_id,xgal,ygal,zgal,rgal,ruwe,mg0,bprp0  from gdr2_contrib.starhorse as s where s.SH_OUTFLAG LIKE '00000' AND s.SH_GAIAFLAG LIKE '000' "
+    i=0
+    for offset in range(0, total, limit):
+        sql = qstr +' LIMIT %s OFFSET %s' % (limit, offset)
+        print(sql)
+        job =     tap_service.submit_job(sql, language='postgresql', runid='batch'+str(i))
+        job.run()
+        jobs.append(job)
+        i=i+1
+    
+    i=0
+    dfvec=[]
+    # collect the results
+    for job in jobs:
+        print('getting results:',i)
+        job.raise_if_error()
+        results = job.fetch_result()
+        dfvec.append(results.to_table().to_pandas())
+        i=i+1
+    i=0
+    
+    print('combining...')
+    df=pd.concat(dfvec)
+    return df
+
+
+
+
+
+
+
+
+
+
+
+
+import streamlit as st
+# To make things easier later, we're also importing numpy and pandas for
+# working with sample data.
+import numpy as np
+import pandas as pd
+import plotly.express as px
+import matplotlib.pyplot as plt
+import seaborn as sns
+from scipy.stats import norm
+
+
+cols=[
+    'dist05', 'dist16', 'dist50', 'dist84', 'dist95',
+    'av05','av16', 'av50', 'av84', 'av95',
+    'teff16', 'teff50', 'teff84',
+    'logg16','logg50', 'logg84',
+    'met16', 'met50', 'met84',
+    'mass16', 'mass50','mass84',
+    'ag50', 'abp50', 'arp50',
+    'mg0', 'bprp0',
+    'xgal', 'ygal',
+    'zgal', 'rgal',
+    'ruwe'
+]
+
+map_cols=[
+    #'dist05', 'dist16', 
+    'dist50', 
+    #'dist84', 'dist95', 
+    #'av05','av16', 
+    #'av50', 
+    #'av84', 'av95', 
+   # 'teff16', 
+    'teff50', 
+   # 'teff84', 
+   # 'logg16',
+    'logg50',
+   # 'logg84', 
+   # 'met16', 
+    'met50',
+   # 'met84', 
+   # 'mass16', 
+    'mass50',
+   # 'mass84', 
+  #  'ag50', 
+  #  'abp50', 
+  #  'arp50', 
+    'mg0', 'bprp0',
+    'xgal', 'ygal','zgal', 
+  #  'rgal', 
+   # 'ruwe'
+]
+
+#suppress_st_warning=True)
+
+@st.cache
+def gendata(Nstars=1000):
+    dfsh=pd.read_parquet(
+        "~/data/sh_tmp.parq",columns=cols).head(Nstars)#.sample(frac=0.02,random_state=42)
+    selection=dfsh.dist50<10
+    df = dfsh[selection]#pd.DataFrame(
+         #{"x":dfsh.xgal,"y":dfsh.ygal,"y":dfsh.ygal})
+    dflen=len(df)
+    df=genmap(df)
+    return df
+
+
+def plot_figure_matplotlib(df, xname,yname,colorname):
+    plt.scatter(
+        df[xname].values, df[yname].values,
+        c=df[colorname], s=0.3, cmap='Spectral', alpha=1.0)
+    st.pyplot()
+
+def plot_figure_plotly(df,xname,yname):
+    #df = gendata()
+    fig = px.scatter(df, x=xname, y=yname, title="title")
+    st.plotly_chart(fig)
+   
+
+
+## Main rendering part
+
+
+st.title('The interactive  maps')
+
+st.write('## selected stars parameters')
+N = st.slider("Pick a number", 1000, 1000000, 10000,100000)
+df = get_data_sql()
+Nstars=len(df)
+st.markdown(f"N = **{Nstars}** stars selected by condition in **gendata()** function")
+
+st.sidebar.markdown('## selected projection parameters')
+
+st.sidebar.markdown('## Plotting parameters')
+xname = st.sidebar.selectbox(
+    'Select the X axis',
+     map_cols,6)
+yname = st.sidebar.selectbox(
+    'Select the Y axis',
+     map_cols,5)
+colorname = st.sidebar.selectbox(
+    'Select the Color axis',
+     map_cols,3)
+
+
+'You selected:', option
+
+
+
+if st.checkbox('Show Scatter plot',value=False):
+    #plot_figure_plotly(df,xname,yname)
+    plot_figure_matplotlib(df, xname,yname,colorname)
+
+if st.checkbox('Show pairwise relationships in a dataset'):
+    sns.pairplot(df[[xname,yname,colorname]])#, hue="a");
+    st.pyplot()
+
+if st.checkbox('Warning: the KDE plots are very slow'):
+    g = sns.PairGrid(df[[xname,yname,colorname]])
+    g.map_diag(sns.kdeplot)
+    g.map_offdiag(sns.kdeplot, n_levels=8);
+    st.pyplot()
+