john-adeojo

import torch
from torch import nn
import torch.nn.functional as F
import transformers
from transformers import Trainer


class FocalLoss(nn.Module):
    def __init__(self, alpha=0.25, gamma=2, reduction='mean'):
        super(FocalLoss, self).__init__()

john-adeojo

exclude_train = ["year", "total_cases", "week_start_date", "city"]
exclude_test = ["year", "week_start_date", "city"]

dp = DataProcessor(
    df_train=df, 
    df_test=test_features_df, 
    exclude_test=exclude_test, 
    exclude_train=exclude_train,
    scaling = 'standardise',
    iq_date_split = '2008-09-30',

john-adeojo

import pandas as pd
import numpy as np
from sklearn.preprocessing import StandardScaler, OneHotEncoder, MinMaxScaler

class DataProcessor:
    def __init__(self, df_train, df_test, exclude_train, exclude_test, scaling, sj_date_split, iq_date_split):
        self.exclude_train = exclude_train
        self.exclude_test = exclude_test
        self.df_train_in = df_train.copy()
        self.df_test_in = df_test.copy()

john-adeojo

import pandas as pd
import numpy as np


# Create labels and features
def features_labels(df):
    y = list(df["gender"].astype("category").cat.codes)
    X = list((df["general_twitter_text"]))
    return y, X

john-adeojo

import sys 
import pandas as pd
import numpy as np
import re

class DataProcessor:
    
    def __init__(self, df):
        self.df = df.copy()
    

john-adeojo

from scipy.stats import ks_2samp

# Run a montecarlo simulation over 1,000 turns to get distribution of KS scores for each
def KS_MonteCarlo(euro_league, n_teams, n_seasons):
    simulation = np.arange(1,1001,1)
    ks_run =[]
    for run in simulation:
        flat20 = perfect_competition(n_teams, n_seasons).T.to_numpy().flatten()
        ks_run.append(ks_2samp(euro_league.Pts, flat20).statistic)
    

john-adeojo

import pandas as pd 
import numpy as np
import random
from itertools import combinations

def simulate_naive(n_teams):
  #Simulate a single season'
    scores = np.zeros(n_teams, dtype=int)
    for i, j in combinations(range(n_teams), 2):
      # each pair of teams play twice, each time with 50/50 chance of 

john-adeojo

League	No. of Winners	Winning Teams	Total Teams in League	Winners as % of Teams in League
Premier League	4	Man City, Liverpool, Chelsea, Leicester, Man Utd	20	20%
La Liga 	3	Atletico Madrid, Real Madrid, Barcelona	20	15%
Ligue 1 	5	Lille, PSG, Monaco, Montpellier	20	25%
Boundesliga	2	Bayern Munich, Borussia Dortmund	18	11%
Eresdivisie	3	Ajax, PSV, Feyenoord	18	17%

john-adeojo

streamlit run yourfile.py

john-adeojo

# Knowledge engine question and answer
if button:
    response_json = openai.Answer.create(
        search_model="ada",
        model="davinci",
        question=question,
        file=openai.File.list()['data'][-1]['id'],  # Get latest file
        examples_context= "In 2017, U.S. life expectancy was 78.6 years." ,
        examples=[["What is human life expectancy in the United States?", "78 years."]],
        max_rerank=300,