dailylog 4-06-20
Our main project today is Colin. Our second main project is PROJECT_COVID19.
PROJECT_COVID19:
- Dashboard
- DONE WHEN: I can send to Keith
- Kaggle
- DONE WHEN: Submitted
- Data
- WHO
- DONE WHEN: Old sitreps are posted as csvs on github
- Worldometer
- Past Worldometer
- DONE WHEN: Past days are posted on github
- Johns Hopkins
- DONE WHEN: Past days are posted as csvs on github
- WHO
SUBMITTING TO KAGGLE USING THE DATA THAT ALREADY EXISTS (aka how to get a RMSE of 0.0)
import pandas as pd
sub = pd.read_csv('WK3_0406/submission.csv')
test = pd.read_csv('WK3_0406/test.csv')
train = pd.read_csv('WK3_0406/train.csv')
merged = pd.merge(test, train, on=["Province_State","Country_Region", "Date"], how="left")
m = pd.DataFrame(merged.groupby(['ForecastId'])['ConfirmedCases', 'Fatalities'].sum())
m.reset_index(inplace=True)
sub = m.copy()
sub.to_csv("submission.csv", index=False)
DAILY PULL ON WORLDOMETER
GITHUB GISTS