Streamlining the changing of standards

Now we can see if there are any major differences in our return. Here, we can also test, historically, how the various types of strategies we might consider employing actually do. It's useful at this point to go ahead and make changing standards easier. This is a better way of doing it, and probably should have been done this way from the start.

import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm, preprocessing
import pandas as pd
from matplotlib import style
import statistics

from collections import Counter


how_much_better = 5

FEATURES =  ['DE Ratio',
             'Trailing P/E',
             'Profit Margin',
             'Operating Margin',
             'Return on Assets',
             'Return on Equity',
             'Revenue Per Share',
             'Market Cap',
             'Enterprise Value',
             'Forward P/E',
             'PEG Ratio',
             'Enterprise Value/Revenue',
             'Enterprise Value/EBITDA',
             'Gross Profit',
             'Net Income Avl to Common ',
             'Diluted EPS',
             'Earnings Growth',
             'Revenue Growth',
             'Total Cash',
             'Total Cash Per Share',
             'Total Debt',
             'Current Ratio',
             'Book Value Per Share',
             'Cash Flow',
             'Held by Insiders',
             'Held by Institutions',
             'Shares Short (as of',
             'Short Ratio',
             'Short % of Float',
             'Shares Short (prior ']

def Status_Calc(stock, sp500):
    difference = stock - sp500

    if difference > how_much_better:
        return 1
        return 0

def Build_Data_Set():
    data_df = pd.DataFrame.from_csv("key_stats_acc_perf_NO_NA_enhanced.csv")

    #data_df = data_df[:100]
    data_df = data_df.reindex(np.random.permutation(data_df.index))
    data_df = data_df.replace("NaN",0).replace("N/A",0)

    data_df["Status2"] = list(map(Status_Calc, data_df["stock_p_change"], data_df["sp500_p_change"]))

    X = np.array(data_df[FEATURES].values)#.tolist())

    y = (data_df["Status2"]

    X = preprocessing.scale(X)

    Z = np.array(data_df[["stock_p_change","sp500_p_change"]])

    return X,y,Z

def Analysis():

    test_size = 1

    invest_amount = 10000
    total_invests = 0

    if_market = 0
    if_strat = 0

    X, y, Z = Build_Data_Set()

    clf = svm.SVC(kernel="linear", C= 1.0)[:-test_size],y[:-test_size])

    correct_count = 0

    for x in range(1, test_size+1):
        if clf.predict(X[-x])[0] == y[-x]:
            correct_count += 1

        if clf.predict(X[-x])[0] == 1:
            invest_return = invest_amount + (invest_amount * (Z[-x][0]/100))
            market_return = invest_amount + (invest_amount * (Z[-x][1]/100))
            total_invests += 1
            if_market += market_return
            if_strat += invest_return

    data_df = pd.DataFrame.from_csv("forward_sample_NO_NA.csv")

    data_df = data_df.replace("N/A",0).replace("NaN",0)

    X = np.array(data_df[FEATURES].values)

    X = preprocessing.scale(X)

    Z = data_df["Ticker"].values.tolist()

    invest_list = []

    for i in range(len(X)):
        p = clf.predict(X[i])[0]
        if p == 1:

    return invest_list

final_list = []

loops = 8

for x in range(loops):
    stock_list = Analysis()
    for e in stock_list:

x = Counter(final_list)

for each in x:
    if x[each] > loops - (loops/3):

That's it for this specific SVM via Linear SVC series, you can either move on to

Or head to the for other tutorials.

  • Intro to Machine Learning with Scikit Learn and Python
  • Simple Support Vector Machine (SVM) example with character recognition
  • Our Method and where we will be getting our Data
  • Parsing data
  • More Parsing
  • Structuring data with Pandas
  • Getting more data and meshing data sets
  • Labeling of data part 1
  • Labeling data part 2
  • Finally finishing up the labeling
  • Linear SVC Machine learning SVM example with Python
  • Getting more features from our data
  • Linear SVC machine learning and testing our data
  • Scaling, Normalizing, and machine learning with many features
  • Shuffling our data to solve a learning issue
  • Using Quandl for more data
  • Improving our Analysis with a more accurate measure of performance in relation to fundamentals
  • Learning and Testing our Machine learning algorithm
  • More testing, this time including N/A data
  • Back-testing the strategy
  • Pulling current data from Yahoo
  • Building our New Data-set
  • Searching for investment suggestions
  • Raising investment requirement standards
  • Testing raised standards
  • Streamlining the changing of standards