!pip install numerapi
import numerapi
NAPI = numerapi.NumerAPI(verbosity="info")
import numpy as np
import random as rn
import pandas as pd
import seaborn as sns
import lightgbm as lgb
import matplotlib.pyplot as plt
from scipy.stats import spearmanr, pearsonr
from sklearn.metrics import mean_absolute_error
import os
​
DIR = "/kaggle/working"
def download_current_data(directory: str):
        """
        Downloads the data for the current round
        :param directory: The path to the directory where the data needs to be saved
        """
        current_round = NAPI.get_current_round()
        if os.path.isdir(f'{directory}/numerai_dataset_{current_round}/'):
            print(f"You already have the newest data! Current round is: {current_round}")
        else:
            print(f"Downloading new data for round: {current_round}!")
            NAPI.download_current_dataset(dest_path=directory, unzip=True)
​
def load_data(directory: str, reduce_memory: bool=True) -> tuple:
        """
        Get data for current round
        :param directory: The path to the directory where the data needs to be saved
        :return: A tuple containing the datasets
        """
        print('Loading the data')
        full_path = f'{directory}/numerai_dataset_{NAPI.get_current_round()}/'
        train_path = full_path + 'numerai_training_data.csv'
        test_path = full_path + 'numerai_tournament_data.csv'
        train = pd.read_csv(train_path)
        test = pd.read_csv(test_path)
        # Reduce all features to 32-bit floats
        if reduce_memory:
            num_features = [f for f in train.columns if f.startswith("feature")]
            train[num_features] = train[num_features].astype(np.float32)
            test[num_features] = test[num_features].astype(np.float32)
        val = test[test['data_type'] == 'validation']
        test = test[test['data_type'] != 'validation']
        return train, val, test
    # Download, unzip and load data
download_current_data(DIR)
train, val, test = load_data(DIR, reduce_memory=True)

def get_group_stats(df: pd.DataFrame) -> pd.DataFrame:
        for group in ["intelligence", "wisdom", "charisma", "dexterity", "strength", "constitution"]:
            cols = [col for col in df.columns if group in col]
            df[f"feature_{group}_mean"] = df[cols].mean(axis=1)
            df[f"feature_{group}_std"] = df[cols].std(axis=1)
            df[f"feature_{group}_skew"] = df[cols].skew(axis=1)
        return df
train = get_group_stats(train)
val = get_group_stats(val)
test = get_group_stats(test)

from sklearn import preprocessing
ft_corr_list=['feature_dexterity7', 'feature_charisma18', 'feature_charisma63', 'feature_dexterity14']#Please try other features!
interactions = preprocessing.PolynomialFeatures(degree=2, interaction_only=True, include_bias=False)
​
interactions.fit(train[ft_corr_list], train["target"])
​
X_train_interact = pd.DataFrame(interactions.transform(train[ft_corr_list]))
X_best_val_inter =pd.DataFrame(interactions.transform(val[ft_corr_list]))
X_best_test_inter =pd.DataFrame(interactions.transform(test[ft_corr_list]))
​
train=pd.concat([train,X_train_interact],axis=1)
​
val=val.reset_index().drop(columns='index')
val=pd.concat([val,X_best_val_inter],axis=1)
​
test=test.reset_index().drop(columns='index')
test=pd.concat([test,X_best_test_inter],axis=1)

feature_list = train.columns.drop(['id','era','data_type','target'])
dtrain = lgb.Dataset(train[feature_list].fillna(0), label=train["target"])
dvalid = lgb.Dataset(val[feature_list].fillna(0), label=val["target"])
​
best_config ={"objective":"regression", "num_leaves":31,"learning_rate":0.01,"n_estimators":2000,"max_depth":5,"metric":"mse","verbosity": 10, "random_state": 0} 
​
model = lgb.train(best_config, dtrain)
​
train.loc[:, "prediction"] = model.predict(train[feature_list])
​
val.loc[:,"prediction"]=val["target"]
val.loc[:,"prediction"] = model.predict(val[feature_list])

def sharpe_ratio(corrs: pd.Series) -> np.float32:
        """
        Calculate the Sharpe ratio for Numerai by using grouped per-era data
​
        :param corrs: A Pandas Series containing the Spearman correlations for each era
        :return: A float denoting the Sharpe ratio of your predictions.
        """
        return corrs.mean() / corrs.std()
​
​
def evaluate(df: pd.DataFrame) -> tuple:
        """
        Evaluate and display relevant metrics for Numerai 
​
        :param df: A Pandas DataFrame containing the columns "era", "target" and a column for predictions
        :param pred_col: The column where the predictions are stored
        :return: A tuple of float containing the metrics
        """
        def _score(sub_df: pd.DataFrame) -> np.float32:
            """Calculates Spearman correlation"""
            return spearmanr(sub_df["target"], sub_df["prediction"])[0]
​
        # Calculate metrics
        corrs = df.groupby("era").apply(_score)
        print(corrs)
        payout_raw = (corrs / 0.2).clip(-1, 1)
        spearman = round(corrs.mean(), 4)
​
        payout = round(payout_raw.mean(), 4)
        numerai_sharpe = round(sharpe_ratio(corrs), 4)
        mae = mean_absolute_error(df["target"], df["prediction"]).round(4)
​
        # Display metrics
        print(f"Spearman Correlation: {spearman}")
        print(f"Average Payout: {payout}")
        print(f"Sharpe Ratio: {numerai_sharpe}")
        print(f"Mean Absolute Error (MAE): {mae}")
        return spearman, payout, numerai_sharpe, mae
​
feature_spearman_val = [spearmanr(val["prediction"], val[f])[0] for f in feature_list]
feature_exposure_val = np.std(feature_spearman_val).round(4)
spearman, payout, numerai_sharpe, mae = evaluate(val)

test.loc[:, "prediction"] =0
test.loc[:, "prediction"] = model.predict(test[feature_list])
test[['id', "prediction"]].to_csv("submission_test.csv", index=False)
​
val[['id', "prediction"]].to_csv("submission_val.csv", index=False)
​
test=0
val=0
​
directory = "/kaggle/working"
full_path = f'{directory}/numerai_dataset_{NAPI.get_current_round()}/'
​
test_path = full_path + 'numerai_tournament_data.csv'
​
tournament_data = pd.read_csv(test_path)
tournament_data_id=tournament_data['id']
tournament_data_id2=tournament_data['feature_dexterity7']
tournament_data_id=pd.concat([tournament_data_id,tournament_data_id2],axis=1)
​
val=pd.read_csv("submission_val.csv")
test=pd.read_csv("submission_test.csv")
​
test_val_concat=pd.concat([val[['id', "prediction"]],test[['id', "prediction"]]],axis=0).set_index('id')
tournament_data_id=tournament_data_id.set_index('id')
​
conc_submit=pd.concat([tournament_data_id,test_val_concat],axis=1).drop(columns='feature_dexterity7').reset_index()
conc_submit=conc_submit.rename(columns={'index': 'id'})
conc_submit.to_csv("submission_file"+".csv", index=False)

def neutralize(series,by, proportion):
    scores = series.values.reshape(-1, 1)
    exposures = by.values.reshape(-1, 1)
    exposures = np.hstack((exposures, np.array([np.mean(series)] * len(exposures)).reshape(-1, 1)))
    correction = proportion * (exposures.dot(np.linalg.lstsq(exposures, scores)[0]))
    corrected_scores = scores - correction
    neutralized = pd.Series(corrected_scores.ravel(), index=series.index)
    return neutralized
​
by=pd.read_csv('/kaggle/working/numerai_dataset_'+str(NAPI.get_current_round())+'/example_predictions.csv')
​
neut=pd.read_csv("submission_file.csv")
neut=pd.DataFrame({'prediction':neutralize(neut['prediction'],by['prediction'], 0.3)})
​
conc=pd.concat([by.drop(columns="prediction"),neut],axis=1)
conc.to_csv("neutralized_submission_file.csv", index=False)#submission file