seekm/elon_py
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

+probability(unfinished)

Browse Source
This commit is contained in:
NY 2025-03-14 15:08:29 +08:00
parent 5a30d6f20f
commit a8125246c2
5 changed files with 292 additions and 124 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
pkg/dash/app_html.py
View File

@ -88,7 +88,7 @@ def layout_config(app):
}
),
html.A(
href='https://x.com/elonmusk',
href='https://x.com/elonmusk/with_replies',
target='_blank',
children=[
html.Img(
@ -193,7 +193,38 @@ def layout_config(app):
style={'width': '100%'}
)
)
])
]),
html.Tr([
html.Td("Predict Tweets Start:", style={'paddingRight': '10px'}),
html.Td(
dcc.Input(
id='prob-start-input',
type='number',
placeholder='输入 Probability Start 值',
value=525,
style={'width': '100%'}
)
)
]),
html.Tr([
html.Td("Predict Tweets End:", style={'paddingRight': '10px'}),
html.Td(
dcc.Input(
id='prob-end-input',
type='number',
placeholder='输入 Probability End 值',
value=549,
style={'width': '100%'}
)
)
]),
html.Tr([
html.Td("Calculate Probability:", style={'paddingRight': '10px'}),
html.Td(
html.Button('Calculate', id='update-button', n_clicks=0)
)
]),
html.Tr(id='manual-info-tooltip', style={'margin': '10px'})
], style={
'width': '50%',
'marginTop': '10px',

95
pkg/dash/func/info.py
View File

@ -1,9 +1,7 @@
import pytz
from pkg.tool import get_tweets_since_last_friday, format_time_str, get_time_since_last_tweet, get_hourly_weighted_array
from pkg.dash.func.info_func import *
from pkg.tool import format_time_str, get_time_since_last_tweet
from pkg.dash.app_init import app
from dash.dependencies import Input, Output
from datetime import timedelta
from datetime import datetime
from dash import html
@ -87,92 +85,3 @@ def update_info(n, target_value, increment_value, hour_value):
})
return [pace_table]
def get_pace_params():
est = pytz.timezone('US/Eastern')
now = datetime.now(est)
today = now.date()
days_to_next_friday = (4 - today.weekday()) % 7
next_friday = (now.replace(hour=12, minute=0, second=0, microsecond=0) +
timedelta(days=days_to_next_friday))
if now > next_friday:
next_friday += timedelta(days=7)
days_to_next_friday = (next_friday - now).total_seconds() / (24 * 60 * 60)
tweet_count = get_tweets_since_last_friday()
return tweet_count, days_to_next_friday
def calculate_tweet_pace():
tweet_count, days_to_next_friday = get_pace_params()
pace = (tweet_count / (7 - days_to_next_friday)) * days_to_next_friday + tweet_count
return round(pace, 6) if pace > 0 else float(tweet_count)
def calculate_pace_decline_rate():
tweet_count, days_to_next_friday = get_pace_params()
T = 7
decline_per_day = -(tweet_count * T) / ((T - days_to_next_friday) ** 2)
decline_per_hour = decline_per_day / 24
return round(decline_per_hour, 2)
def calculate_pace_for_increment(increment, hours, tweet_count, days_to_next_friday, current_pace):
future_days = days_to_next_friday - (hours / 24)
new_tweet_count = tweet_count + increment
if future_days <= 0:
return round(new_tweet_count, 2)
new_pace = (new_tweet_count / (7 - future_days)) * future_days + new_tweet_count
return round(max(new_pace, new_tweet_count), 2)
def calculate_pace_increase_in_hour(increment_value, hour_value):
tweet_count, days_to_next_friday = get_pace_params()
current_pace = (tweet_count / (7 - days_to_next_friday)) * days_to_next_friday + tweet_count
increments = [0, 1, 5, 10, 20]
pace_increases = {}
for inc in increments:
pace_increases[f'increase_{inc}'] = calculate_pace_for_increment(
inc, 1, tweet_count, days_to_next_friday, current_pace
)
if increment_value is None or hour_value is None:
pace_increases['custom_increment'] = None
else:
increment = int(increment_value)
hours = int(hour_value)
pace_increases['custom_increment'] = calculate_pace_for_increment(
increment, hours, tweet_count, days_to_next_friday, current_pace
)
pace_increases['custom_increment_key'] = increment
return pace_increases
def calculate_avg_tweets_per_day(target, now, remain):
Xi = get_hourly_weighted_array()
if remain <= 0:
return "remain<=0"
if target <= now:
return "Already reach"
fx = max(remain - 12, 0)
if remain > 12:
fy = sum(Xi[0:12]) * 24
else:
full_hours = int(remain)
fractional_hour = remain - full_hours
if full_hours >= 24:
full_hours = 23
fractional_hour = 0
if full_hours < 0:
full_hours = 0
if full_hours > 0:
fy = sum(Xi[0:full_hours]) + Xi[full_hours] * fractional_hour
else:
fy = Xi[0] * fractional_hour
fy *= 24
if fx + fy == 0:
return "fx + fy = 0"
result = (target - now) / ((fx + fy) / 24)
return round(result, 2)

218
pkg/dash/func/info_func.py Normal file
View File

@ -0,0 +1,218 @@
import pytz
from pkg.tool import get_tweets_since_last_friday, aggregate_data
import numpy as np
from scipy.stats import norm
from datetime import timedelta, datetime
from pkg.config import render_data
def get_last_7_days_data():
est = pytz.timezone('US/Eastern')
now = datetime.now(est).date()
last_7_days = [now - timedelta(days=i) for i in range(7)]
data = render_data.global_agg_df[
render_data.global_agg_df['date'].isin(last_7_days)].copy()
return data
def get_hourly_weighted_array():
data = get_last_7_days_data()
if data.empty:
return [1 / 24] * 24
agg_data = aggregate_data(data, 60)
one_day_data = agg_data.groupby('interval_group')['tweet_count'].sum().reset_index()
tweet_count_total = one_day_data['tweet_count'].sum()
hourly_rates = [0] * 24
for _, row in one_day_data.iterrows():
minute = row['interval_group']
hour = int(minute // 60)
if hour < 24:
hourly_rates[hour] = row['tweet_count'] / tweet_count_total if tweet_count_total > 0 else 0
total_rate = sum(hourly_rates)
if total_rate > 0:
hourly_rates = [rate / total_rate for rate in hourly_rates]
else:
hourly_rates = [1 / 24] * 24
return hourly_rates
def calculate_variance_factor():
data = get_last_7_days_data()
if data.empty or 'tweet_count' not in data.columns:
return 1.5
data['hour'] = data['minute_of_day'] // 60
hourly_data = data.groupby(['date', 'hour'])['tweet_count'].sum().reset_index()
hourly_stats = hourly_data.groupby('hour')['tweet_count'].agg(['mean', 'var']).reset_index()
variance_factors = hourly_stats['var'] / hourly_stats['mean']
return np.mean(variance_factors[variance_factors.notna()]) or 1.5
def get_dynamic_hourly_weights():
data = get_last_7_days_data()
if data.empty:
return [1 / 24] * 24
weights = [0.2, 0.2, 0.3, 0.3, 0.5, 0.5, 0.5]
hourly_rates = [0] * 24
for day_idx, day in enumerate(get_last_7_days_data()['date'].unique()):
day_data = data[data['date'] == day].copy()
if day_data.empty:
continue
agg_data = aggregate_data(day_data, 60)
day_tweets = agg_data.groupby('interval_group')['tweet_count'].sum().reset_index()
day_total = day_tweets['tweet_count'].sum()
for _, row in day_tweets.iterrows():
minute = row['interval_group']
hour = int(minute // 60)
if hour < 24:
hourly_rates[hour] += (row['tweet_count'] / day_total if day_total > 0 else 0) * weights[day_idx % 7]
total_rate = sum(hourly_rates)
if total_rate > 0:
hourly_rates = [rate / total_rate for rate in hourly_rates]
else:
hourly_rates = [1 / 24] * 24
return hourly_rates
def get_pace_params():
est = pytz.timezone('US/Eastern')
now = datetime.now(est)
today = now.date()
days_to_next_friday = (4 - today.weekday()) % 7
next_friday = (now.replace(hour=12, minute=0, second=0, microsecond=0) +
timedelta(days=days_to_next_friday))
if now > next_friday:
next_friday += timedelta(days=7)
days_to_next_friday = (next_friday - now).total_seconds() / (24 * 60 * 60)
tweet_count = get_tweets_since_last_friday()
return tweet_count, days_to_next_friday
def calculate_tweet_pace():
tweet_count, days_to_next_friday = get_pace_params()
pace = (tweet_count / (7 - days_to_next_friday)) * days_to_next_friday + tweet_count
return round(pace, 6) if pace > 0 else float(tweet_count)
def calculate_pace_decline_rate():
tweet_count, days_to_next_friday = get_pace_params()
T = 7
decline_per_day = -(tweet_count * T) / ((T - days_to_next_friday) ** 2)
decline_per_hour = decline_per_day / 24
return round(decline_per_hour, 2)
def calculate_pace_for_increment(increment, hours, tweet_count, days_to_next_friday, current_pace):
future_days = days_to_next_friday - (hours / 24)
new_tweet_count = tweet_count + increment
if future_days <= 0:
return round(new_tweet_count, 2)
new_pace = (new_tweet_count / (7 - future_days)) * future_days + new_tweet_count
return round(max(new_pace, new_tweet_count), 2)
def calculate_pace_increase_in_hour(increment_value, hour_value):
tweet_count, days_to_next_friday = get_pace_params()
current_pace = (tweet_count / (7 - days_to_next_friday)) * days_to_next_friday + tweet_count
increments = [0, 1, 5, 10, 20]
pace_increases = {}
for inc in increments:
pace_increases[f'increase_{inc}'] = calculate_pace_for_increment(
inc, 1, tweet_count, days_to_next_friday, current_pace
)
if increment_value is None or hour_value is None:
pace_increases['custom_increment'] = None
else:
increment = int(increment_value)
hours = int(hour_value)
pace_increases['custom_increment'] = calculate_pace_for_increment(
increment, hours, tweet_count, days_to_next_friday, current_pace
)
pace_increases['custom_increment_key'] = increment
return pace_increases
def calculate_avg_tweets_per_day(target, now, remain):
Xi = get_hourly_weighted_array()
if remain <= 0:
return "remain<=0"
if target <= now:
return "Already reach"
fx = max(remain - 12, 0)
if remain > 12:
fy = sum(Xi[0:12]) * 24
else:
full_hours = int(remain)
fractional_hour = remain - full_hours
if full_hours >= 24:
full_hours = 23
fractional_hour = 0
if full_hours < 0:
full_hours = 0
if full_hours > 0:
fy = sum(Xi[0:full_hours]) + Xi[full_hours] * fractional_hour
else:
fy = Xi[0] * fractional_hour
fy *= 24
if fx + fy == 0:
return "fx + fy = 0"
result = (target - now) / ((fx + fy) / 24)
return round(result, 2)
def calculate_tweet_probability(tweet_count, days_to_next_friday, prob_start, prob_end, peak_percentile=75):
remaining_hours = days_to_next_friday * 24
hourly_weights = get_dynamic_hourly_weights()
data = get_last_7_days_data()
if data.empty:
recent_tweets = [70] * 7
else:
agg_data = aggregate_data(data, 1440)
daily_tweets = agg_data.groupby('date')['tweet_count'].sum().reset_index()
recent_tweets = daily_tweets['tweet_count'].tolist()[-7:]
if len(recent_tweets) < 7:
recent_tweets = recent_tweets + [70] * (7 - len(recent_tweets))
recent_3_days = np.mean(recent_tweets[-3:])
past_4_days = np.mean(recent_tweets[:-3]) if len(recent_tweets) > 3 else 70
daily_avg = 0.8 * recent_3_days + 0.2 * past_4_days
daily_avg_std = np.std(recent_tweets) if len(recent_tweets) >= 7 else np.std([70] * 7)
peak_threshold = np.percentile(hourly_weights, peak_percentile)
segments = []
current_segment = []
for i in range(24):
if hourly_weights[i] >= peak_threshold:
current_segment.append(i)
elif current_segment:
segments.append(current_segment)
current_segment = []
if current_segment:
segments.append(current_segment)
lambda_remaining = 0
variance_factor = calculate_variance_factor()
total_weight = sum(hourly_weights)
for segment in segments:
hours_in_segment = len(segment) * (remaining_hours / 24)
segment_weight_avg = np.mean([hourly_weights[i] for i in segment])
lambda_segment = daily_avg * (hours_in_segment / remaining_hours) * (segment_weight_avg / (total_weight / 24))
lambda_remaining += lambda_segment
mu_low = (daily_avg - daily_avg_std) * (remaining_hours / 24)
mu_high = (daily_avg + daily_avg_std) * (remaining_hours / 24)
var_low = mu_low * variance_factor
var_high = mu_high * variance_factor
sigma_low = np.sqrt(var_low)
sigma_high = np.sqrt(var_high)
a = prob_start - tweet_count
b = prob_end - tweet_count
if a < 0:
return "0.0000 - 0.0000" if tweet_count > prob_end else "1.0000 - 1.0000"
prob_low = norm.cdf((b - mu_low) / sigma_low) - norm.cdf((a - mu_low) / sigma_low)
prob_high = norm.cdf((b - mu_high) / sigma_high) - norm.cdf((a - mu_high) / sigma_high)
return f"{prob_low:.4f} - {prob_high:.4f}"

37
pkg/dash/func/info_m.py Normal file
View File

@ -0,0 +1,37 @@
from pkg.dash.func.info_func import *
from pkg.dash.app_init import app
from dash.dependencies import Input, Output
from dash import html
@app.callback(
[Output('manual-info-tooltip', 'children')],
[Input('update-button', 'n_clicks'),
Input('prob-start-input', 'value'),
Input('prob-end-input', 'value')]
)
def update_info_manual(n_clicks, prob_start, prob_end):
if n_clicks == 0:
return [html.Div("Click 'Manual Update' to see results.")]
tweet_count, days_to_next_friday = get_pace_params()
prob_start = int(prob_start) if prob_start is not None else 525
prob_end = int(prob_end) if prob_end is not None else 549
probability = calculate_tweet_probability(tweet_count, days_to_next_friday, prob_start, prob_end)
prob_low, prob_high = map(float, probability.split(" - "))
formatted_probability = f"{prob_low * 100:.2f}% - {prob_high * 100:.2f}%"
pace_table_rows = [
html.Tr([
html.Th(f"Probability ({prob_start}-{prob_end})", colSpan=2, style={'paddingRight': '10px'}),
html.Td(formatted_probability, colSpan=6, style={'paddingRight': '10px'})
])
]
pace_table = html.Table(pace_table_rows, style={
'width': '100%',
'textAlign': 'left',
'borderCollapse': 'collapse'
})
return [pace_table]

31
pkg/tool.py
View File

@ -1,5 +1,6 @@
from datetime import datetime, timedelta
import pandas as pd
import numpy as np
from pkg.config import render_data
import pytz
@ -84,7 +85,7 @@ def get_time_since_last_tweet():
return 0.0
latest_tweet_time = df['datetime_est'].max()
time_diff = now_est - latest_tweet_time
days_diff = time_diff.total_seconds() / (24 * 60 * 60) # 转换为天数
days_diff = time_diff.total_seconds() / (24 * 60 * 60)
return days_diff
def format_time_str(days_to_next_friday):
@ -97,31 +98,3 @@ def format_time_str(days_to_next_friday):
return f"{days}d {hours:02d}h {minutes:02d}m {seconds:02d}s ({total_hours}h)"
def get_hourly_weighted_array():
est = pytz.timezone('US/Eastern')
now = datetime.now(est).date()
last_7_days = [now - timedelta(days=i) for i in range(7)]
multi_data_agg = render_data.global_agg_df[
render_data.global_agg_df['date'].isin(last_7_days)].copy()
if multi_data_agg.empty:
return [1 / 24] * 24
agg_data = aggregate_data(multi_data_agg, 60)
one_day_data = agg_data.groupby('interval_group')['tweet_count'].sum().reset_index()
tweet_count_total = one_day_data['tweet_count'].sum()
hourly_rates = [0] * 24
for _, row in one_day_data.iterrows():
minute = row['interval_group']
hour = int(minute // 60)
if hour < 24:
hourly_rates[hour] = row['tweet_count'] / tweet_count_total if tweet_count_total > 0 else 0
total_rate = sum(hourly_rates)
if total_rate > 0:
hourly_rates = [rate / total_rate for rate in hourly_rates]
else:
hourly_rates = [1 / 24] * 24
return hourly_rates