File size: 4,667 Bytes
f842047
a134d9b
 
 
 
ddd4c40
03b33db
ddd4c40
72f2521
a46bb55
 
ac1c55d
a46bb55
 
309bf92
11a5d2b
c005138
a46bb55
a134d9b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f497c67
 
 
a46bb55
 
 
 
a134d9b
 
 
 
 
c005138
f842047
d125423
 
a134d9b
 
 
f842047
 
 
a134d9b
11a5d2b
35989d5
a46bb55
c9eef1d
d125423
 
 
35989d5
c005138
11a5d2b
 
35989d5
 
 
c9eef1d
d125423
 
 
35989d5
 
c005138
11a5d2b
 
0e4b180
 
ac1c55d
0e4b180
 
 
ac1c55d
11a5d2b
 
d125423
a134d9b
a46bb55
11a5d2b
773f144
 
a46bb55
773f144
a46bb55
773f144
 
309bf92
 
 
 
 
 
 
 
79bdafd
 
 
 
 
a46bb55
 
 
 
a134d9b
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
from datetime import datetime
import gradio as gr
import pandas as pd
import duckdb
import logging

from tabs.tokens_dist import (
    get_extreme_cases,
)
from tabs.dist_gap import (
    get_distribution_plot,
    get_avg_gap_time_evolution_grouped_markets,
    get_correlation_map,
    get_kde_with_trades,
    get_kde_with_total_bet_amount,
    get_dist_gap_time_evolution,
    get_dist_gap_timeline_plotly,
)


def get_logger():
    logger = logging.getLogger(__name__)
    logger.setLevel(logging.DEBUG)
    # stream handler and formatter
    stream_handler = logging.StreamHandler()
    stream_handler.setLevel(logging.DEBUG)
    formatter = logging.Formatter(
        "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
    )
    stream_handler.setFormatter(formatter)
    logger.addHandler(stream_handler)
    return logger


logger = get_logger()


def prepare_data():
    """
    Get all data from the parquet files
    """
    logger.info("Getting all data")
    con = duckdb.connect(":memory:")

    # Query to fetch invalid trades data
    query = f"""
    SELECT *
    FROM read_parquet('./live_data/markets_live_data.parquet')
    """
    df = con.execute(query).fetchdf()
    df["sample_datetime"] = df["sample_timestamp"].apply(
        lambda x: datetime.fromtimestamp(x)
    )
    df["opening_datetime"] = df["openingTimestamp"].apply(
        lambda x: datetime.fromtimestamp(int(x))
    )
    df["days_to_resolution"] = (df["opening_datetime"] - df["sample_datetime"]).dt.days
    return df


demo = gr.Blocks()
markets_data = prepare_data()
markets_data["sample_date"] = pd.to_datetime(markets_data["sample_datetime"]).dt.date
live_markets_data = markets_data.loc[markets_data["open"] == True]
# filter only those with trades
markets_data = markets_data.loc[markets_data["total_trades"] > 0]
with demo:
    gr.HTML("<h1>Olas Predict Live Markets </h1>")
    gr.Markdown("This app shows the distributions of predictions on the live markets.")
    best_market_id, best_gap, worst_market_id, worst_gap = get_extreme_cases(
        live_markets_data
    )
    with gr.Tabs():
        with gr.TabItem("💹 Probability distributions of some markets"):
            with gr.Row():
                gr.Markdown("Best case: a market with a low gap between distributions")
            with gr.Row():
                gr.Markdown(
                    f"Market id = {best_market_id} Dist gap = {round(best_gap,2)}"
                )
            with gr.Row():
                best_case = get_dist_gap_timeline_plotly(
                    best_market_id, live_markets_data
                )

            with gr.Row():
                gr.Markdown("Worst case: a market with a high distribution gap metric")
            with gr.Row():
                gr.Markdown(
                    f"Market id = {worst_market_id} Dist gap = {round(worst_gap,2)}"
                )

            with gr.Row():
                worst_case = get_dist_gap_timeline_plotly(
                    worst_market_id, live_markets_data
                )
            with gr.Row():
                gr.Markdown(
                    "Time evolution of the average distribution gap percentage of markets created the same day"
                )

            with gr.Row():
                mean_plot = get_avg_gap_time_evolution_grouped_markets(markets_data)

        with gr.TabItem("📏 Distribution gap metric for all markets"):
            # remove samples with no trades
            with gr.Row():
                gr.Markdown(
                    "This metric measures the difference between the probability distribution based on the tokens distribution and the one based on the price weighted distribution"
                )
            with gr.Row():
                gr.Markdown("# Density distribution")
            with gr.Row():
                kde_plot = get_distribution_plot(markets_data)

            with gr.Row():
                with gr.Column(min_width=350):
                    gr.Markdown("# Relationship with number of trades")
                    kde_trades_plot = get_kde_with_trades(markets_data)
                with gr.Column(min_width=350):
                    gr.Markdown("# Relationship with total bet amount")
                    kde_total_bet_amount_plot = get_kde_with_total_bet_amount(
                        markets_data
                    )

            with gr.Row():
                gr.Markdown(
                    "# Correlation analysis between the metric and market variables"
                )

            with gr.Row():
                correlation_plot = get_correlation_map(markets_data)

    demo.queue(default_concurrency_limit=40).launch()