prratek

from starlette.applications import Starlette
from starlette.responses import HTMLResponse, JSONResponse
from starlette.staticfiles import StaticFiles
from starlette.middleware.cors import CORSMiddleware
import uvicorn, aiohttp, asyncio
from io import BytesIO

from fastai import *
from fastai.vision import *

prratek

m = RandomForestRegressor(n_estimators=100, max_features='log2', n_jobs=-1)
m.fit(X_train, y_train)
print_score(m)

prratek

m = RandomForestRegressor(max_features='sqrt', n_jobs=-1)
m.fit(X_train, y_train)
print_score(m)

prratek

m = RandomForestRegressor(max_features='log2', n_jobs=-1)
m.fit(X_train, y_train)
print_score(m)

prratek

m = RandomForestRegressor(n_jobs=-1)
m.fit(X_train, y_train)
print_score(m)

prratek

import numpy as np
import matplotlib.pyplot as plt
from sklearn import metrics

preds = np.stack([t.predict(X_valid) for t in m.estimators_])
preds[:,0], np.mean(preds[:,0])
plt.plot([metrics.r2_score(y_valid, np.mean(preds[:i+1], axis=0)) for i in range(10)]);

prratek

import pandas as pd
from sklearn.ensemble import RandomForestRegressor

n = 100   # use every 100th row
df = pd.read_csv('{PATH_TO_DATA}train.csv', skiprows=lambda i: i % n != 0)

m = RandomForestRegressor()   # instantiate the RandomForestRegressor objects
m.fit(X_train, y_train)   # train the model
m.score(X_valid, y_valid)   # score it on your validation set