import dash
from dash import Dash, html, dcc, callback, Output, Input
import plotly.express as px
from app import app
import pandas as pd

import datetime
import requests
from io import StringIO
from datetime import date

# from jupyter_dash import JupyterDash
# from dash.dependencies import Input, Output
import dash_bootstrap_components as dbc
import plotly.express as px

server = app.server

url='https://drive.google.com/file/d/1NaXOYHQFF5UO5rQr4rn8Lr3bkYMSOq4_/view?usp=sharing'
url='https://drive.google.com/uc?id=' + url.split('/')[-2]

# reading of file
df = pd.read_csv(url)

df['date'] = pd.to_datetime(df['date'])

unique_domains = df['domain_folder_name'].unique()
print(unique_domains)

unique_topics = df['Topic'].unique()
print(unique_topics)

#copying a column 
df["Veículos de notícias"] = df["domain_folder_name"]

# df = df.rename(columns={df.columns[4]: "Veículos de notícias"})

df['FinBERT_label'] = df['FinBERT_label'].astype(str)
df['FinBERT_label'].replace({
    '3.0': 'positive',
    '2.0': 'neutral',
    '1.0': 'negative'
}, inplace=True)



counts = df.groupby(['date', 'Topic', 'domain_folder_name', 'FinBERT_label']).size().reset_index(name='count')
counts['count'] = counts['count'].astype('float64')
counts['rolling_mean_counts'] = counts['count'].rolling(window=30, min_periods=2).mean()

df_pos = counts[[x in ['positive'] for x in counts.FinBERT_label]]
df_neu = counts[[x in ['neutral'] for x in counts.FinBERT_label]]
df_neg = counts[[x in ['negative'] for x in counts.FinBERT_label]]



app.layout = dbc.Container([   
    dbc.Row([ # row 1
        dbc.Col([html.H1('Evolução temporal de sentimento em títulos de notícias')],
        className="text-center mt-3 mb-1")]),
    
    dbc.Row([ # row 2
        dbc.Label("Selecione um período (mm/dd/aaaa):", className="fw-bold")]),

    dbc.Row([ # row 3
        dcc.DatePickerRange(
            id='date-range',
            min_date_allowed=df['date'].min().date(),
            max_date_allowed=df['date'].max().date(),
            initial_visible_month=df['date'].min().date(),
            start_date=df['date'].min().date(),
            end_date=df['date'].max().date())]),

    dbc.Row([ # row 4
        dbc.Label("Escolha um tópico:", className="fw-bold")
    ]),

    dbc.Row([ # row 5
        dbc.Col(
            dcc.Dropdown(
                id="topic-selector",
                options=[
                    {"label": topic, "value": topic} for topic in unique_topics
                ],
                value="Imigrantes",  # Set the initial value
                style={"width": "50%"})


        )
    ]),
    
    dbc.Row([ # row 6
            dbc.Col(dcc.Graph(id='line-graph-1'))
    ]),

    dbc.Row([ # row 7 but needs to be updated
        dbc.Col(dcc.Graph(id="bar-graph-1"))
    ]),

    dbc.Row([ # row 7
            dbc.Label("Escolha um site de notícias:", className="fw-bold")
    ]),

    dbc.Row([ # row 8
        dbc.Col(
            dcc.Dropdown(
                id="domain-selector",
                options=[
                    {"label": domain, "value": domain} for domain in unique_domains
                ],
                value="expresso-pt",  # Set the initial value
                style={"width": "50%"})


        )
    ]),

    dbc.Row([ # row 9
            dbc.Col(dcc.Graph(id='line-graph-2'),
                    )
    ]),

    dbc.Row([ # row 10
            dbc.Col(dcc.Graph(id='line-graph-3'),
                    )
    ]),
    
    dbc.Row([ # row 11
            dbc.Col(dcc.Graph(id='line-graph-4'),
                    )
    ]),

    html.Div(id='pie-container-1')

])
# # Create a function to generate pie charts
# def generate_pie_chart(category):
#     labels = data[category]['labels']
#     values = data[category]['values']
#     trace = go.Pie(labels=labels, values=values)
#     layout = go.Layout(title=f'Pie Chart - {category}')
#     return dcc.Graph(
#         figure={
#             'data': [trace],
#             'layout': layout
#         }
#     )
    
# callback decorator
@app.callback(
    Output('line-graph-1', 'figure'),
    Output('bar-graph-1','figure'),
    Output('line-graph-2', 'figure'),
    Output('line-graph-3', 'figure'),
    Output('line-graph-4', 'figure'),
    Output('pie-container-1', 'children'),
    Input("topic-selector", "value"),
    Input ("domain-selector", "value"),
    Input('date-range', 'start_date'),
    Input('date-range', 'end_date')
)
def update_output(selected_topic, selected_domain, start_date, end_date):
    #log
    print("topic",selected_topic,"domain",selected_domain,"start", start_date,"date", end_date)
    
    # filter dataframes based on updated data range
    mask_1 = ((df["Topic"] == selected_topic) & (df['date'] >= start_date) & (df['date'] <= end_date))
    df_filtered = df.loc[mask_1]
    print(df_filtered.shape)
    if len(df_filtered)>0:
        #create line graphs based on filtered dataframes
        line_fig_1 = px.line(df_filtered, x="date", y="normalised results",
                         color='Veículos de notícias', title="O gráfico mostra a evolução temporal de sentimento dos títulos de notícias. Numa escala de -1 (negativo) a 1 (positivo), sendo 0 (neutro).")
    
        # Veículos de notícias
        #set x-axis title and y-axis title in line graphs
        line_fig_1.update_layout(
                       xaxis_title='Data',
                       yaxis_title='Classificação de Sentimento')
    
        #set label format on y-axis in line graphs
        line_fig_1.update_xaxes(tickformat="%b %d<br>%Y")
    
        # Bar Graph start
        grouped_df = df_filtered.groupby(['date', 'Veículos de notícias']).size().reset_index(name='occurrences')
        
        # Sort DataFrame by 'period' column
        grouped_df = grouped_df.sort_values(by='date')
        
        # Create a list of all unique media
        all_media = df_filtered['domain_folder_name'].unique()
        
        # Create a date range from Jan/2000 to the last month in the dataset
        date_range = pd.date_range(start=df_filtered['date'].min().date(), end=df_filtered['date'].max().date(), freq='MS')
        
        # Create a MultiIndex with all combinations of date_range and all_media
        idx = pd.MultiIndex.from_product([date_range, all_media], names=['date', 'Veículos de notícias'])
        
        # Reindex the DataFrame to include all periods and media
        grouped_df = grouped_df.set_index(['date', 'Veículos de notícias']).reindex(idx, fill_value=0).reset_index()
    
        bar_fig_1 = px.bar(grouped_df, x='date', y='occurrences', color='Veículos de notícias',
                 labels={'date': 'Período', 'occurrences': 'Número de notícias', 'Veículos de notícias': 'Portal'},
                 title='Número de notícias por período de tempo')
        bar_fig_1.update_xaxes(tickformat="%b %d<br>%Y")
        # Bar Graph ends
                           
        # filter dataframes based on updated data range
        mask_2 = ((df_pos["Topic"] == selected_topic) & (df_pos["domain_folder_name"] == selected_domain) & (df_pos['date'] >= start_date) & (df_pos['date'] <= end_date))
        mask_3 = ((df_neu["Topic"] == selected_topic) & (df_neu["domain_folder_name"] == selected_domain) & (df_neu['date'] >= start_date) & (df_neu['date'] <= end_date))
        mask_4 = ((df_neg["Topic"] == selected_topic) & (df_neg["domain_folder_name"] == selected_domain) & (df_neg['date'] >= start_date) & (df_neg['date'] <= end_date))
        df2_filtered = df_pos.loc[mask_2]
        df3_filtered = df_neu.loc[mask_3]
        df4_filtered = df_neg.loc[mask_4]
    
    #create line graphs based on filtered dataframes
        line_fig_2 = px.line(df2_filtered, x="date", y="rolling_mean_counts", line_group="FinBERT_label",
                         title="Positive")
        line_fig_3 = px.line(df3_filtered, x="date", y="rolling_mean_counts", line_group="FinBERT_label",
                         title="Neutral")
        line_fig_4 = px.line(df4_filtered, x="date", y="rolling_mean_counts", line_group="FinBERT_label",
                         title="Negative")
    
    #set x-axis title and y-axis title in line graphs
        line_fig_2.update_layout(
                       xaxis_title='Data',
                       yaxis_title='Número de notícias com sentimento positivo')
        line_fig_3.update_layout(
                       xaxis_title='Data',
                       yaxis_title='Número de notícias com sentimento neutro')
        line_fig_4.update_layout(
                       xaxis_title='Data',
                       yaxis_title='Número de notícias com sentimento negativo')
    
    #set label format on y-axis in line graphs
        line_fig_2.update_xaxes(tickformat="%b %d<br>%Y")
        line_fig_3.update_xaxes(tickformat="%b %d<br>%Y")
        line_fig_4.update_xaxes(tickformat="%b %d<br>%Y")
    
    #set label format on y-axis in line graphs
        line_fig_2.update_traces(line_color='#1E88E5')
        line_fig_3.update_traces(line_color='#004D40')
        line_fig_4.update_traces(line_color='#D81B60')

    #
        # pie_container_1 = generate_pie_chart(category)
        # Map original labels to their translated versions
        label_translation = {'positive': 'positivo', 'neutral': 'neutro', 'negative': 'negativo'}
        df_filtered['FinBERT_label_transformed'] = df_filtered['FinBERT_label'].map(label_translation)
        
        # Group by FinBERT_label and count occurrences
        label_counts_all = df_filtered['FinBERT_label_transformed'].value_counts()
        
        # Calculate percentage of each label
        label_percentages_all = (label_counts_all / label_counts_all.sum()) * 100
        
        # Plot general pie chart
        fig_general = px.pie(
            values=label_percentages_all,
            names=label_percentages_all.index,
            title='Distribuição Geral',
            color_discrete_sequence=['#039a4d', '#3c03f4', '#ca3919']
        )
        
        
        # Get unique media categories
        media_categories = df_filtered['Veículos de notícias'].unique()
        
        # Define colors for each label
        label_colors = {'positivo': '#039a4d', 'neutro': '#3c03f4', 'negativo': '#ca3919'}
        
                         
        pie_container_1 = []
        # Loop through each media category
        row_content = []
        for media in media_categories:
            # Filter DataFrame for current media category
            media_df = df_filtered[df_filtered['Veículos de notícias'] == media]
        
            # Group by FinBERT_label and count occurrences
            label_counts = media_df['FinBERT_label_transformed'].value_counts()
        
            # Calculate percentage of each label
            label_percentages = (label_counts / label_counts.sum()) * 100
        
            # Plot pie chart
            fig = px.pie(
                values=label_percentages,
                names=label_percentages.index,
                title=f'Distribuição para {media}',
                color_discrete_sequence=[label_colors[label] for label in label_percentages.index]
            )
            fig = dcc.Graph(figure=fig)
            pie_chart = html.Div(fig,className='four columns')
            row_content.append(pie_chart)
        pie_container_1.append(html.Div(row_content, className='row'))
            
        return line_fig_1, bar_fig_1, line_fig_2, line_fig_3, line_fig_4, pie_container_1
    else:
        return {'data': []},{'data': []} ,{'data': []} ,{'data': []} , {'data': []}, {'data':[]} 
    
    # return line_fig_1
    


# df = pd.read_csv('https://raw.githubusercontent.com/plotly/datasets/master/gapminder_unfiltered.csv')



# app.layout = html.Div([
#     html.H1(children='Title of Dash App', style={'textAlign':'center'}),
#     dcc.Dropdown(df.country.unique(), 'Canada', id='dropdown-selection'),
#     dcc.Graph(id='graph-content')
# ])

# @callback(
#     Output('graph-content', 'figure'),
#     Input('dropdown-selection', 'value')
# )
# def update_graph(value):
#     dff = df[df.country==value]
#     return px.line(dff, x='year', y='pop')


if __name__ == '__main__':
    app.run_server(debug=True)