Upload Covid19.py

apps/Covid19.py

@@ -1,3 +1,369 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9bf0ff7418785c629693b8fba73e40116a1918f6c2272a98e7d415a3c94a17e1
-size 15184
+import streamlit as st
+from plotly import graph_objs as go
+import pandas as pd
+from pandas.core.groupby.groupby import DataError
+from pytrends.request import TrendReq
+from datetime import datetime, timedelta, date
+import numpy as np
+from plotly.subplots import make_subplots
+from metodos import colores_corporativos
+import pybase64 as base64
+import io
+from logs_portal import log
+from Scheduler import Scheduler_Covid as sc
+import os
+
+def button_style():
+    style_button = """
+        <style>
+      button {
+        margin-top:-100px;
+        display: inline-block;
+        background-color: #e8e8e8;
+        border-radius: 15px;
+        border: 4px  #cccccc;
+        color: #4a4a4a;
+        text-align: center;
+        font-size: 15px;
+        padding: 2px;
+        width: 260px;
+        transition: all 0.5s;
+        cursor: pointer;
+        margin: 5px;
+      }
+      button span {
+        cursor: pointer;
+        display: inline-block;
+        position: relative;
+        transition: 0.5s;
+      }
+      button span:after {
+        content: '\00bb';
+        position: absolute;
+        opacity: 0;
+        top: 0;
+        right: -20px;
+        transition: 0.5s;
+      }
+      button:hover {
+        background-color: #bb1114;
+        color:#e8e8e8;
+      }
+      button:hover span {
+        padding-right: 25px;
+      }
+      button:hover span:after {
+        opacity: 1;
+        right: 0;
+      }
+    </style>
+    """
+    st.markdown(style_button, unsafe_allow_html=True)
+
+
+def get_table_download_link(df):
+    """Generates a link allowing the data in a given panda dataframe to be
+    downloaded
+    in:  dataframe
+    out: href string
+    """
+    csv = df.to_csv(index=False)
+    b64 = base64.b64encode(csv.encode()).decode()
+    name_arch = "Scoring_filtrado.csv"
+    name_mark = "Descargar .csv "
+    style = '"color:black;text-decoration: none;font-size:18px;"'
+    href = f'<center><a href="data:file/csv;base64,{b64}" style='  + style+' download="'+name_arch+'" ><button>'+name_mark+'</button></a></center>'
+    return href
+
+
+def get_table_excel_link(df, name_arch):
+    towrite = io.BytesIO()
+    downloaded_file = df.to_excel(towrite, encoding='utf-8', index=False,
+                                  header=True)
+    towrite.seek(0)  # reset pointer
+    file_name = name_arch
+    style = 'style="color:black;text-decoration: none; font-size:18px;" '
+    name_mark = "Descargar "+name_arch
+    b64 = base64.b64encode(towrite.read()).decode()  # some strings
+    linko= f'<center><a href="data:application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;base64,{b64}" '+style+'download="'+file_name+'"><button>'+name_mark+'</button></a></center>'
+    return linko
+
+
+@st.cache(show_spinner=True)
+def charged_data():
+    regiones = {}
+    regiones['Latam'] = ['Argentina', 'Brazil', 'Chile', 'Colombia',
+                         'Mexico', 'Peru']
+    regiones['Europa'] = ['Italy', 'Spain', 'Germany', 'United Kingdom',
+                          'France']
+    regiones['Asia Emergente'] = ['South Korea', 'Taiwan', 'Hong Kong',
+                                  'India', 'Thailand', 'Indonesia']
+    regiones['USA'] = ['United States']
+    data_dict = np.load('Scheduler/dict_movilidad.npy',
+                        allow_pickle='TRUE').item()
+    return data_dict, regiones
+
+
+@st.cache(show_spinner=True)
+def charged_data2():
+    covid_data = pd.read_csv('https://covid.ourworldindata.org/data/owid-covid-data.csv')
+    paises = {'CL': 'Chile', 'AR': 'Argentina', 'BR': 'Brazil',
+              'MX': 'Mexico'}
+    covid_data = covid_data.loc[covid_data['location'].isin(paises.values())]
+    covid_data['date'] = pd.to_datetime(covid_data['date'])
+    covid_data.set_index(['date', 'location'], inplace=True)
+    # Creamos diccionario con cada una de las variables para distintos países
+    data_dict = {}
+    for col in covid_data.columns:
+        try:
+            data_dict[col] = covid_data[col].unstack().fillna(0).rolling(1).mean()
+        except DataError:
+            pass
+    # Descargamos la data de google trends
+    pytrends = TrendReq(retries=5, backoff_factor=0.2,
+                        requests_args={'verify': False})
+    start = (datetime.today() - timedelta(180)).strftime("%Y-%m-%d")
+    start = datetime(2020, 2, 1).strftime("%Y-%m-%d")
+    end = datetime.today().strftime("%Y-%m-%d")
+    tf = f'{start} {end}'
+    kw_lists = {
+                'CL': ['PCR', 'sintomas covid', 'examen covid',
+                       'covid positivo'],
+                'AR': ['PCR', 'olfato', 'sintomas covid', 'perdida gusto',
+                       'covid positivo'],
+                'MX': ['PCR', 'olfato', 'sintomas covid', 'covid positivo',
+                       'perdida gusto'],
+                'BR': ['PCR', 'sintomas covid', 'exame covid', 'covid positivo']
+                }
+    gt_data = {}
+    for p, kw in kw_lists.items():
+        pytrends.build_payload(kw, timeframe=tf, geo=p)
+        df = pytrends.interest_over_time().drop(columns='isPartial')
+        gt_data[paises[p]] = df.div(df.mean(0).values)
+    data_dict['GT Index'] = pd.DataFrame({p: gt_data[p].mean(1).rolling(1).mean()
+                                          for p in gt_data.keys()})
+    return data_dict, paises
+
+
+@log
+def Movilidad():
+    largo = 400
+    ancho = 550
+    button_style()
+    placebar = st.empty()
+    percent_complete = 0
+    my_bar = placebar.progress(percent_complete)
+    data_cargada = charged_data()
+    data_dict = data_cargada[0]
+    regiones = data_cargada[1]
+    europa = data_dict['Mobility Index'][regiones.keys()]["Europa"]
+    latam = data_dict['Mobility Index'][regiones.keys()]["Latam"]
+    asia = data_dict['Mobility Index'][regiones.keys()]["Asia Emergente"]
+    USA = data_dict['Mobility Index'][regiones.keys()]["USA"]
+    mov_region = data_dict['Mobility Index'][regiones.keys()][["USA", "Europa","Asia Emergente", "Latam"]]
+    percent_complete = percent_complete+33
+    placebar.progress(percent_complete)
+    colores = list(colores_corporativos().values())
+    colores2 = []
+    for i in range(len(colores)):
+        colores2.append("rgb"+str(colores[i]))
+    def plot_raw_data():
+        fig = go.Figure()
+        europa_ = go.Scatter(x=europa.index, y=europa.values, name="Europa",
+                             line=dict(color=colores2[0]))
+        latam_ = go.Scatter(x=latam.index, y=latam.values, name="Latam",
+                            line=dict(color=colores2[1]))
+        USA_ = go.Scatter(x=USA.index, y=USA.values, name="USA",
+                          line=dict(color=colores2[2]))
+        asia_ = go.Scatter(x=asia.index, y=asia.values, name="Asia Emergente",
+                           line=dict(color=colores2[3]))
+        fig.add_trace(europa_)
+        fig.add_trace(latam_)
+        fig.add_trace(USA_)
+        fig.add_trace(asia_)
+        fig.layout.update(title_text="Evolución por region",
+                          xaxis_rangeslider_visible=True,
+                          margin_b=20,
+                          margin_r=20,
+                          margin_l=20,
+                          width=ancho,
+                          height=largo,
+                          legend=dict(orientation="h",
+                                      yanchor="bottom",
+                                      y=1.02,
+                                      xanchor="right",
+                                      x=1))
+        fig2 = go.Figure()
+        i = 0
+        for pais in regiones["Latam"]:
+            data_pais = data_dict['Mobility Index'][regiones['Latam']][pais]
+            pais_gr = go.Scatter(x=data_pais.index,
+                                 y=data_pais.values, name=pais,
+                                 line=dict(color=colores2[i]))
+            fig2.add_trace(pais_gr)
+            i = i+1
+        fig2.layout.update(title_text="Evolución LATAM",
+                           xaxis_rangeslider_visible=True, margin_b=20,
+                           margin_r=20,margin_l=20,
+                           width=ancho, height=largo,
+                           legend=dict(orientation="h",
+                                       yanchor="bottom",
+                                       y=1.0,
+                                       xanchor="right",
+                                       x=1))
+        col1, col2 = st.columns(2)
+        col1.plotly_chart(fig, use_container_width=True)
+        col2.plotly_chart(fig2, use_container_width=True)
+        link_excel_1 = get_table_excel_link(data_dict['Mobility Index'][regiones['Latam']], "Movilidad Latam.xlsx")
+        link_excel_2 = get_table_excel_link(mov_region, "Movilidad por region.xlsx")
+        col1.markdown(link_excel_1, unsafe_allow_html=True)
+        col2.markdown(link_excel_2, unsafe_allow_html=True)
+    percent_complete = percent_complete + 33
+    placebar.progress(percent_complete)
+    placebar.empty()
+    plot_raw_data()
+    percent_complete = percent_complete + 34
+    my_bar.progress(percent_complete)
+    my_bar.empty()
+    data_desag = pd.read_excel("Scheduler/Movilidad_desagrada.xlsx",
+                               engine="openpyxl")
+    st.markdown(get_table_excel_link(data_desag, "Movilidad desagregada.xlsx"),
+                unsafe_allow_html=True)
+    try:
+        user = os.getlogin()
+        if user == 'bullm':
+            act = st.button('Actualizar')
+            if act:
+                sc.run_data_covid()
+                ud = pd.read_excel('Data/update_data.xlsx')
+                ud = ud[ud['View'] != 'Covid19']
+                today = date.today().strftime('%d-%m-%Y')
+                ud = ud.append({"View": "Covid19",
+                                "Last_Update": today}, ignore_index=True)
+                ud.to_excel('Data/update_data.xlsx', index=False)
+    except Exception:
+        pass
+
+
+@log
+def Correlacion_GT():
+    largo = 400
+    ancho = 550
+    button_style()
+    # Cargamos la data relevante
+    percent_complete = 0
+    my_bar = st.progress(percent_complete)
+    percent_complete = percent_complete + 33
+    my_bar.progress(percent_complete)
+    data_cargada = charged_data2()
+    data_dict = data_cargada[0]
+    paises = data_cargada[1]
+    corr_df = pd.DataFrame(index=paises.values(), columns=np.arange(-3, 1))
+    percent_complete = percent_complete + 33
+    my_bar.progress(percent_complete)
+    i = 0
+    cols = st.columns(2)
+    col1, col2, col3, col4 = st.columns((1.5, 7, 2, 7))
+    for p in corr_df.index:
+        df = pd.concat([data_dict['GT Index'][p],
+                        data_dict['new_cases_per_million'][p]],
+                       axis=1).dropna()
+        df.columns = ['GT Index', 'Nuevos Casos Confirmados']
+        fig = make_subplots(specs=[[{"secondary_y": True}]])
+        CC = go.Scatter(x=df['GT Index'].index,
+                        y=df['GT Index'].values, name='GT index',
+                        line=dict(color='dimgrey'))
+        GT = go.Scatter(x=df['Nuevos Casos Confirmados'].index,
+                        y=df['Nuevos Casos Confirmados'].values,
+                        name='Casos confirmados', line=dict(color='darkred'))
+        fig.add_trace(CC, secondary_y=False,)
+        fig.add_trace(GT, secondary_y=True,)
+        fig.layout.update(title_text="Evolución {}".format(p),
+                          xaxis_rangeslider_visible=True, margin_b=20,
+                          margin_r=20, margin_l=20,
+                          width=ancho, height=largo,
+                          legend=dict(orientation="h",
+                                      yanchor="bottom",
+                                      y=1.02,
+                                      xanchor="right",
+                                      x=1))
+        link_excel = get_table_excel_link(df, "Correlacion GT.xlsx")
+        if i % 2 == 0:
+            cols[0].plotly_chart(fig, use_container_width=True)
+            cols[0].markdown(link_excel, unsafe_allow_html=True)
+        else:
+            cols[1].plotly_chart(fig, use_container_width=True)
+            cols[1].markdown(link_excel, unsafe_allow_html=True)
+            cols = st.columns(2)
+            col1, col2, col3, col4 = st.columns((1.5, 7, 2, 7))
+        i = i + 1
+    percent_complete = percent_complete + 34
+    my_bar.progress(percent_complete)
+    my_bar.empty()
+
+
+
+@log
+def vacunas():
+    largo = 400
+    ancho = 550
+    button_style()
+    vac_data = pd.read_csv('https://covid.ourworldindata.org/data/owid-covid-data.csv').set_index(['date','location'])
+    country_pop = (vac_data['population'].reset_index().set_index('location')
+                   .drop(columns='date').squeeze().drop_duplicates())
+    min_pop = 1000000
+    idx = country_pop[country_pop > min_pop].index
+    vac_data = vac_data['total_vaccinations_per_hundred'].unstack().ffill().fillna(0)
+    vac_data.index = pd.to_datetime(vac_data.index)
+    N = 15
+    top_vac = vac_data[idx].iloc[-1].nlargest(N).sort_values()
+    regiones = {}
+    regiones['Latam'] = ['Argentina', 'Brazil', 'Chile', 'Colombia',
+                         'Mexico', 'Peru']
+    regiones['Europa'] = ['Italy', 'Spain', 'Germany', 'United Kingdom',
+                          'France', 'Russia']
+    regiones['Asia Emergente'] = ['South Korea', 'Taiwan', 'Hong Kong',
+                                  'China', 'Japan']
+    regiones['Norteamérica'] = ['United States', 'Canada']
+    inicio = datetime(2020, 11, 15)
+    vac_data = vac_data.loc[vac_data.index > inicio].resample('W').last()
+    vac_data.index.name = ''
+    colores = colores_corporativos().values()
+    colores = list(colores_corporativos().values())
+    colores2 = []
+    for i in range(len(colores)):
+        colores2.append("rgb"+str(colores[i]))
+
+    def plot_raw_data():
+        i = 0
+        cols = st.columns(2)
+        col1, col2, col3, col4 = st.columns((1.5, 7, 2, 7))
+        for region in list(regiones.keys()):
+            fig = go.Figure()
+            j = 0
+            for pais in regiones[region]:
+                data_pais = vac_data[regiones[region]][pais]
+                pais_gr = go.Scatter(x=data_pais.index,
+                                     y=data_pais.values, name=pais,
+                                     line=dict(color=colores2[j]))
+                fig.add_trace(pais_gr)
+                j = j+1
+            fig.layout.update(title_text="Evolución "+region,
+                              xaxis_rangeslider_visible=True, height=largo,
+                              width=ancho, margin_b=20,
+                              legend=dict(orientation="h",
+                                          yanchor="bottom",
+                                          y=1.0,
+                                          xanchor="right",
+                                          x=1))
+            link_excel = get_table_excel_link(data_pais, "Vacunacion.xlsx")
+            if i % 2 == 0:
+                cols[0].plotly_chart(fig, use_column_width=True)
+                cols[0].markdown(link_excel, unsafe_allow_html=True)
+            else:
+                cols[1].plotly_chart(fig, use_column_width=True)
+                cols[1].markdown(link_excel, unsafe_allow_html=True)
+                cols = st.columns(2)
+                col1, col2, col3, col4 = st.columns((1.5, 7, 2, 7))
+            i = i+1
+    plot_raw_data()