|
from datetime import datetime, timedelta |
|
import gradio as gr |
|
import matplotlib.pyplot as plt |
|
import pandas as pd |
|
import seaborn as sns |
|
import duckdb |
|
import logging |
|
from tabs.tokens_votes_dist import ( |
|
get_based_tokens_distribution, |
|
get_based_votes_distribution, |
|
) |
|
|
|
|
|
def get_logger(): |
|
logger = logging.getLogger(__name__) |
|
logger.setLevel(logging.DEBUG) |
|
|
|
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 = 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) |
|
) |
|
return df |
|
|
|
|
|
def get_extreme_cases(live_fpmms: pd.DataFrame): |
|
"""Function to return the id of the best and worst case according to the dist gap metric""" |
|
|
|
samples_per_market = ( |
|
live_fpmms[["id", "sample_timestamp"]].groupby("id").count().reset_index() |
|
) |
|
markets_with_multiple_samples = list( |
|
samples_per_market.loc[samples_per_market["sample_timestamp"] > 1, "id"].values |
|
) |
|
selected_markets = live_fpmms.loc[ |
|
live_fpmms["id"].isin(markets_with_multiple_samples) |
|
] |
|
selected_markets.sort_values(by="dist_gap_perc", ascending=False, inplace=True) |
|
return selected_markets.iloc[-1].id, selected_markets.iloc[0].id |
|
|
|
|
|
demo = gr.Blocks() |
|
markets_data = prepare_data() |
|
|
|
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, worst_market_id = get_extreme_cases(markets_data) |
|
with gr.Tabs(): |
|
with gr.TabItem("💹 Probability distributions of live markets"): |
|
with gr.Row(): |
|
gr.Markdown("# Evolution of outcomes probability based on tokens") |
|
|
|
with gr.Row(): |
|
gr.Markdown("Best case: a market with a low distribution gap metric") |
|
with gr.Row(): |
|
gr.Markdown(f"Market id = {best_market_id}") |
|
with gr.Row(): |
|
best_market_tokens_dist = get_based_tokens_distribution( |
|
best_market_id, 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}") |
|
|
|
with gr.Row(): |
|
worst_market_tokens_dist = get_based_tokens_distribution( |
|
worst_market_id, markets_data |
|
) |
|
|
|
with gr.Row(): |
|
gr.Markdown("# Evolution of outcomes probability based on votes") |
|
|
|
demo.queue(default_concurrency_limit=40).launch() |
|
|
