SajidLhessani

df = yf.download(sp,period = "3d",interval="15m")

SajidLhessani

df = pd.read_html("http://en.wikipedia.org/wiki/List_of_S%26P_500_companies")[0]

SajidLhessani

# Create a column by name, SMA and assign the SMA calculation to it
df['SMA'] = df['Close'].shift(1).rolling(window=n).mean()

# Create a column by name, Corr and assign the calculation of correlation to it
df['Corr'] = df['Close'].shift(1).rolling(window=n).corr(df['SMA'].shift(1))

# Create a column by name, SAR and assign the SAR calculation to it
df['SAR'] = ta.SAR(np.array(df['High'].shift(1)), np.array(df['Low'].shift(1)),
                   0.2, 0.2)

SajidLhessani

# Create a variable split that stores 80% of the length of the dataframe
t = .8
split = int(t*len(df))
split

SajidLhessani

# Change the value of 'Corr' to -1 if it is less than -1
df.loc[df['Corr'] < -1, 'Corr'] = -1

# Change the value of 'Corr' to 1 if it is greater than 1
df.loc[df['Corr'] > 1, 'Corr'] = 1

# Drop the NaN values
df = df.dropna()

SajidLhessani

# Create a column 'Ret' with the calculation of returns
df['Ret'] = (df['Open'].shift(-1)-df['Open'])/df['Open']

# Create n columns and assign
for i in range(1, n):
    df['return%i' % i] = df['Ret'].shift(i)

SajidLhessani

# Create columns 'OO' with the difference between the current minute's open and last minute's open
df['OO'] = df['Open']-df['Open'].shift(1)

# Create columns 'OC' with the difference between the current minute's open and last minute's close
df['OC'] = df['Open']-df['Prev_Close']

SajidLhessani

# Create columns high, low and close with previous minute's OHLC data
df['Prev_High'] = df['High'].shift(1)
df['Prev_Low'] = df['Low'].shift(1)
df['Prev_Close'] = df['Close'].shift(1)

SajidLhessani

# Create a column by name, SMA and assign the SMA calculation to it
df['SMA'] = df['Close'].shift(1).rolling(window=n).mean()

# Create a column by name, Corr and assign the calculation of correlation to it
df['Corr'] = df['Close'].shift(1).rolling(window=n).corr(df['SMA'].shift(1))

# Create a column by name, SAR and assign the SAR calculation to it
df['SAR'] = ta.SAR(np.array(df['High'].shift(1)), np.array(df['Low'].shift(1)),
                   0.2, 0.2)

SajidLhessani

# Data manipulation libraries
import pandas as pd
import numpy as np

# Machine learning libraries
from sklearn.svm import SVC
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import RandomizedSearchCV
from sklearn.model_selection import TimeSeriesSplit
from sklearn.pipeline import Pipeline