def update_figure(selected_dropdown1, selected_dropdown2, val, fr): dropdown = { 'Coursera': cou_n, 'edX': edx_n, 'Khan Academy': kha_n, 'Pluralsight': plu_n, 'Skillshare': ski_n, 'Udacity': uda_n, 'Udemy': ude_n, 'Skype': sky_n, 'Zoom': zoo_n, 'TED Talks': ted_n } df = dropdown[selected_dropdown1] if val == 1: df1 = df[df['username'] == selected_dropdown1] elif val == 2: df1 = df[df['username'] != selected_dropdown1] else: df1 = df test = data_prep(df1) test_i = seasonal_decompose(test[selected_dropdown2], model='additive', period=fr) t1 = pd.DataFrame(test_i.trend) t1.index = t1.index.to_timestamp().to_pydatetime() figure = { 'data': [{ 'x': t1.index, 'y': t1['trend'], 'range_x': [t1.index.min(), t1.index.max()], 'type': 'scatter', 'mode': 'marker', 'opacity': 0.7 }], 'layout': { 'title': 'Trend analysis of 2019-20 period for {}'.format( selected_dropdown2), 'xaxis': { 'title': 'Timeline' } } } return figure
RUN_CREATE_FEATURE_DATASET = False RUN_CREATE_ROC_CAUSAL_DATASET = False RUN_EXPERIMENTS = False #RUN_CREATE_FEATURE_DATASET also needs to be true '''Latents Dimension for Deconfounder Algorithm (DA)''' k_mf_ = [40] k_pca_ = [40] k_ac_ = [10] '''Loading dataset''' filename = "data\\tcga_train_gexpression_cgc_7k.txt" #_2 filename_gamma = "results\\gamma.txt" #Running Factor Analysis Models + Predictive Check + outcome model in all patients if RUN_ALL: data = pd.read_csv(filename, sep=';') #data = data.iloc[0:500, 0:100] train, j, v, y01, abr, colnames = fc.data_prep(data) #j: rows, v: columns, y01: initial label, abr: cancer type, colnames: genes names ''' 1) Run factor model; 2) Do predictive check; 3) If pass on predictive ckeck, run outcome model 4) Save results and predictions for ROC curve ''' df_gamma = pd.read_csv(filename_gamma, sep=';') gamma = [] cil = [] cip = [] id2 = [] if RUN_MF: for k_mf in k_mf_:
import functions #improvements: change variable names to be more intuitive chdir("/home/cree/Downloads/br_econ/") count = 0 mun, state = {}, {} mun = functions.import_data("mun") state = functions.import_data("state") chdir("/home/cree/workspace/econometrics/") # municipal dataframes mun_renda = functions.data_prep(mun.get('mun/Renda_municipios - Renda familiar - per capita - media.csv')) mun_ensino = functions.data_prep(mun.get('mun/mun_media_anos_de_estudos_25_anos_+_todos.csv')) mun_saude = mun.get('mun/mun_Mortalidade infantil (por mil nascidos vivos)_1970-2000.csv') mun_populacao_censo = functions.data_prep(mun.get('mun/populacao_municipal.csv')) mun_renda_2, mun_ensino_2 = mun_renda.ix[3:].copy(),mun_ensino.ix[3:].copy() mun_renda, mun_ensino = mun_renda.ix[:3],mun_ensino.ix[:3] #state dataframes state_renda = functions.data_prep(state.get('state/estado_Renda domiciliar per capita - media_1976 - 2014.csv')) state_ensino = functions.data_prep(state.get('state/Anos de estudo - media - pessoas 25 anos e mais - 1981 - 2014.csv')) state_ensino_mulheres = functions.data_prep(state.get('state/Anos de estudo - media - pessoas 25 anos e mais - mulheres 1981 -2014.csv')) state_populacao_anual = functions.data_prep(state.get('state/populcao_estado_1980-2014.csv')) state_populacao_censo = state.get('state/populacao_residente_estado_1970-2000.csv') #calcular mortalidade infantil por estado df9 = state_populacao_censo[['Sigla', 'Código', 'Estado']].copy()
def update_figure(selected_dropdown1, val): dropdown = { 'Coursera': cou_n, 'edX': edx_n, 'Khan Academy': kha_n, 'Pluralsight': plu_n, 'Skillshare': ski_n, 'Udacity': uda_n, 'Udemy': ude_n, 'Skype': sky_n, 'Zoom': zoo_n, 'TED Talks': ted_n } df = dropdown[selected_dropdown1] if val == 1: df1 = df[df['username'] == selected_dropdown1] var = selected_dropdown1 + ' handle' elif val == 2: df1 = df[df['username'] != selected_dropdown1] var = 'Users' else: df1 = df var = 'Both (Platform and user)' test = data_prep(df1) test.index = test.index.to_timestamp().to_pydatetime() trace1 = go.Bar(x=test.index, y=test['tweet_counter'] - test['label'], name='Non Covid', hovertext=test['tweet_counter'] - test['label']) trace2 = go.Bar(x=test.index, y=test['label'], name='Covid', hovertext=test['label']) figure1 = go.Figure( data=[trace1, trace2], layout=go.Layout( barmode='stack', title= 'Analysis for Covid and Non-Covid related tweets from {} on a weekly basis ' .format(var), # paper_bgcolor='rgba(48, 48, 48, 1)', plot_bgcolor='white')) df2 = df1[df1['label'] == 1] wc = [len(text) for text in df2['text']] time = [tim for tim in df2['timestamp']] trace3 = go.Scatter(x=time, y=wc, mode='markers', marker={ 'color': '#ff471a', 'size': wc, 'sizemode': 'area', 'sizeref': 2. * max(wc) / (40.**2), 'sizemin': 4 }) figure2 = go.Figure(data=[trace3], layout=go.Layout( plot_bgcolor='white', title='Covid related tweets on timeline')) return figure1, figure2
'Pluralsight': plu_n, 'Skillshare': ski_n, 'Udacity': uda_n, 'Udemy': ude_n, 'Skype': sky_n, 'Zoom': zoo_n, 'TED Talks': ted_n } server = flask.Flask(__name__) app = dash.Dash(__name__, server=server) data = list(dict_main.keys()) # keys for the dataset values channels = dict_main[data[0]] # the_data_sets channels = data_prep(channels) app.layout = html.Div([ html.H1('COVID Edu-Tech', style={'textAlign': 'center'}), html.Div([ html.Div([ html.Label([ "Select Platform", dcc.Dropdown(id='data-dropdown', options=[{ 'label': label, 'value': label } for label in data], value=list(dict_main.keys())[0], multi=False, searchable=False,