68 lines
2.3 KiB
Python
68 lines
2.3 KiB
Python
from sqlalchemy import create_engine
|
|
import pandas as pd
|
|
import pytz
|
|
|
|
# Database connection configuration
|
|
DB_CONFIG = {
|
|
'host': '8.155.23.172',
|
|
'port': 3306,
|
|
'user': 'root2',
|
|
'password': 'tG0f6PVYh18le41BCb',
|
|
'database': 'elonX'
|
|
}
|
|
TABLE_NAME = 'elon_tweets'
|
|
db_uri = f"mysql+pymysql://{DB_CONFIG['user']}:{DB_CONFIG['password']}@{DB_CONFIG['host']}:{DB_CONFIG['port']}/{DB_CONFIG['database']}"
|
|
engine = create_engine(db_uri)
|
|
# Time zone
|
|
eastern = pytz.timezone('America/New_York')
|
|
pacific = pytz.timezone('America/Los_Angeles')
|
|
central = pytz.timezone('America/Chicago')
|
|
# CSV update file path
|
|
INPUT_FILE = 'cache/elonmusk.csv'
|
|
OUTPUT_FILE = 'cache/fixed.csv'
|
|
# Time interval and days options
|
|
interval_options = [
|
|
{'label': '1 minute', 'value': 1},
|
|
{'label': '5 minutes', 'value': 5},
|
|
{'label': '10 minutes', 'value': 10},
|
|
{'label': '30 minutes', 'value': 30},
|
|
{'label': '1 hour', 'value': 60},
|
|
{'label': '6 hours(1/4 day)', 'value': 360},
|
|
{'label': '8 hours(1/3 day)', 'value': 480},
|
|
{'label': '12 hours(1/2 day)', 'value': 720},
|
|
{'label': '1 day', 'value': 1440}
|
|
]
|
|
days_options = [
|
|
{'label': '7 days', 'value': 7},
|
|
{'label': '14 days', 'value': 14},
|
|
{'label': '30 days', 'value': 30},
|
|
{'label': '90 days', 'value': 90},
|
|
{'label': '120 days', 'value': 120},
|
|
{'label': '240 days', 'value': 240}
|
|
]
|
|
|
|
# Global render data
|
|
class RenderData:
|
|
def __init__(self):
|
|
self.global_df = None
|
|
self.global_agg_df = None
|
|
self.all_dates = []
|
|
self.default_date = []
|
|
self.load_data()
|
|
|
|
def load_data(self):
|
|
df = pd.read_sql(f'SELECT timestamp FROM {TABLE_NAME}', con=engine)
|
|
df['datetime'] = pd.to_datetime(df['timestamp'], unit='s')
|
|
df['datetime_est'] = df['datetime'].dt.tz_localize('UTC').dt.tz_convert(eastern)
|
|
df['date'] = df['datetime_est'].dt.date
|
|
df['minute_of_day'] = df['datetime_est'].dt.hour * 60 + df['datetime_est'].dt.minute
|
|
agg_df = df.groupby(['date', 'minute_of_day']).size().reset_index(name='tweet_count')
|
|
|
|
self.global_df = df.copy()
|
|
self.global_agg_df = agg_df.copy()
|
|
self.all_dates = sorted(self.global_agg_df['date'].unique(), reverse=True)
|
|
self.default_date = [str(self.all_dates[0])]
|
|
|
|
render_data = RenderData()
|
|
|