def get_data(value):
start = dt.datetime(2010, 1, 1)
end = pd.to_datetime(dt.datetime.today(),
format='%Y-%m-%d',
errors='coerce')
stk_data = gh(symbol=value, start=start, end=end)
stk_data.reset_index(inplace=True)
return stk_data[['Date', 'Close']]
from pypfopt import risk_models
from pypfopt import expected_returns
from pypfopt.discrete_allocation import DiscreteAllocation, get_latest_prices
stocksymbols = [
'TATAMOTORS', 'DABUR', 'ICICIBANK', 'WIPRO', 'BPCL', 'IRCTC', 'INFY',
'RELIANCE'
]
startdate = date(2019, 10, 14)
end_date = date.today()
print(end_date)
print(f"You have {len(stocksymbols)} assets in your porfolio")
df = pd.DataFrame()
for i in range(len(stocksymbols)):
data = gh(symbol=stocksymbols[i], start=startdate,
end=(end_date))[['Symbol', 'Close']]
data.rename(columns={'Close': data['Symbol'][0]}, inplace=True)
data.drop(['Symbol'], axis=1, inplace=True)
if i == 0:
df = data
if i != 0:
df = df.join(data)
# calculating expected annual return and annualized sample covariance matrix of daily assets returns
mean = expected_returns.mean_historical_return(df)
S = risk_models.sample_cov(df) # for sample covariance matrix
plt.style.use('ggplot')
fig = plt.figure()
def find_profits(symbol, start, end, stocks=50):
df = gh(symbol=symbol, start=start, end=end)
df = dataset(df, stocks)
print(f"Profit: {df['Profits'].sum()}")
return df
from sklearn import model_selection
from sklearn.metrics import confusion_matrix
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
import numpy as np
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.layers import Dropout
#Setting start and end dates and fetching the historical data
start = dt.datetime(2013, 1, 1)
end = dt.datetime(2018, 12, 31)
stk_data = gh(symbol='SBIN', start=start, end=end)
#Visualizing the fetched data
plt.figure(figsize=(14, 14))
plt.plot(stk_data['Close'])
plt.title('Historical Stock Value')
plt.xlabel('Date')
plt.ylabel('Stock Price')
plt.show()
#Data Preprocessing
stk_data['Date'] = stk_data.index
data2 = pd.DataFrame(columns=['Date', 'Open', 'High', 'Low', 'Close'])
data2['Date'] = stk_data['Date']
data2['Open'] = stk_data['Open']
data2['High'] = stk_data['High']
# -*- coding: utf-8 -*-
"""
Created on Wed Jul 22 15:54:07 2020
@author: mukmc
"""
from nsepy import get_history as gh
import datetime as dt
start = dt.datetime(2020,7,20)
end = dt.datetime(2020,7,22)
stk_data = gh(symbol='NIFTY 50',start=start,end=end)
###...........................................................
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
dat = pd.read_csv("data/nifty.csv",index_col=False)
dat['hl']=dat['High']-dat['Low']
dat=dat.reindex(index=dat.index[::-1])
#training_set = dat.iloc[0:int((4862)*0.8),4]
training_set = dat.iloc[0:int((4862)*0.8),1:6]
from sklearn.preprocessing import MinMaxScaler
# Import useful Libraries
from nsepy import get_history as gh
from datetime import date
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import statistics as stats
import math
from sklearn.model_selection import GridSearchCV
from sklearn.linear_model import SGDClassifier
from sklearn.metrics import roc_curve, auc, roc_auc_score
from sklearn.svm import SVC
from sklearn.model_selection import train_test_split
# Get the data required using nsepy
stk1 = gh(symbol='RELIANCE', start=date(2019, 11, 1), end=date(2020, 5, 7))
# We will save the dataframe so that we can keep calling it over and over again
stk1.to_pickle('ril.pkl')
ril = pd.read_pickle('ril.pkl')
# - We will now pose this problem as a classification problem.
# - The idea is that if the adjusted close price the next day is higher than the present day, we buy the stock. This will be indicated as 1. Otherwise, we sell the stock. This will be indicated as 0.
# rilf = pd.DataFrame(index = ril.index)
# rilf['price'] = ril['Last']
ril['response'] = ril['Last'].diff()
ril['class'] = np.where(ril['response'] > 0.0, 1, 0)
ril['class_final'] = ril['class'].shift(
-1) # shift the classes to align the next day with present day
ril = ril.iloc[:len(ril) - 1]
ril['class_final'] = ril.class_final.astype(int)
from nsepy import get_history as gh
from keras.models import Sequential
from keras.layers import Dense, LSTM, Dropout
from sklearn.preprocessing import MinMaxScaler
# CONSTANTS
N_FEATURES = 1 # number of features
N_STEPS = 60 # number of time-steps
TRAIN_SPLIT = 0.8 # portion of data to be trained
# DATA PREPROCESSING
# Loading Data
data = gh(symbol='BHARTIARTL',
start=datetime(2004, 1, 1),
end=datetime(2021, 4, 13))
data = data[['Close']]
final_data = data.values
train_data = final_data[0:int(len(final_data) * TRAIN_SPLIT), :]
test_data = final_data[int(len(final_data) * TRAIN_SPLIT):, :]
# Scaling Data
scaler = MinMaxScaler()
scaled_data = scaler.fit_transform(final_data)
# Train-Test Split
X_train, y_train = [], []
for i in range(N_STEPS, len(train_data)):
X_train.append(scaled_data[i - N_STEPS:i, 0])
y_train.append(scaled_data[i, 0])