Code to analyze each stock

MACD_Analyze_Stocks.py

# Get the path for each stock file in a list
list_files = (glob.glob("<Your Path>\\SMA_Analysis\\Stocks\\*.csv"))
# You can use this line to limit the analysis to a portion of the stocks in the "stocks folder"
# list_files = list_files[:100]
# Create the dataframe that we will be adding the final analysis of each stock to
Compare_Stocks = pd.DataFrame(columns=["Company", "Days_Observed", "Crosses", "True_Positive", "False_Positive", "True_Negative", "False_Negative", "Sensitivity", 
"Specificity", "Accuracy", "TPR", "FPR"])
# While loop to cycle through the stock paths
count = 0
for stock in list_files:
    # Dataframe to hold the historical data of the stock we are interested in.
    Hist_data = pd.read_csv(stock)
    Company = ((os.path.basename(stock)).split(".csv")[0])  # Name of the company
    # Constants for the stock that we will be updating later
    Days_Observed = 0
    Crosses = 0
    True_Positive = 0
    False_Positive = 0
    True_Negative = 0
    False_Negative = 0
    Sensitivity = 0
    Specificity = 0
    Accuracy = 0
    # This list holds the closing prices of a stock
    prices = []
    c = 0
    # Add the closing prices to the prices list and make sure we start at greater than 2 dollars to reduce outlier calculations.
    while c < len(Hist_data):
        if Hist_data.iloc[c,4] > float(2.00):  # Check that the closing price for this day is greater than $2.00
            prices.append(Hist_data.iloc[c,4])
        c += 1
    prices_df = pd.DataFrame(prices)  # Make a dataframe from the prices list
    # Calculate exponentiall weighted moving averages:
    day12 = prices_df.ewm(span=12).mean()  #
    day26 = prices_df.ewm(span=26).mean()
    macd = []  # List to hold the MACD line values
    counter=0  # Loop to substantiate the MACD line
    while counter < (len(day12)):
        macd.append(day12.iloc[counter,0] - day26.iloc[counter,0])  # Subtract the 26 day EW moving average from the 12 day.
        counter += 1
    macd_df = pd.DataFrame(macd)
    signal_df = macd_df.ewm(span=9).mean() # Create the signal line, which is a 9 day EW moving average
    signal = signal_df.values.tolist()  # Add the signal line values to a list.
    #  Loop to Compare the expected MACD crosses results to the actual results
    Day = 1
    while Day < len(macd)-5: # -1 to be able to use the last day for prediction, -5 so we can look at the 5 day post average.
        Prev_Day = Day-1
        # Avg_Closing_Next_Days = (prices[Day+1] + prices[Day+2] + prices[Day+3] + prices[Day+4] + prices[Day+5])/5 # To use 5 day average as a decision.
        Avg_Closing_Next_Days = (prices[Day+1] + prices[Day+2] + prices[Day+3])/3  # To use 3 day average as a decision.
        Days_Observed += 1  # Count how many days were observed
        if ((signal[Prev_Day] > macd[Prev_Day]) and (signal[Day] <= macd[Day])):  # when the signal line dips below the macd line (Expected increase over the next x days)
            Crosses += 1   # register that a cross occurred
            if (prices[Day] < Avg_Closing_Next_Days):  # Tests if the price increases over the next x days.
                True_Positive += 1
            else:
                False_Negative += 1

        if ((signal[Prev_Day] < macd[Prev_Day]) and (signal[Day] >= macd[Day])): # when the signal line moves above the macd line (Expected dip over the next x days)
            Crosses += 1
            if (prices[Day] > Avg_Closing_Next_Days):  # Tests if the price decreases over the next x days.
                True_Negative += 1
            else:
                False_Positive += 1
        Day += 1
    try:
        Sensitivity = (True_Positive / (True_Positive + False_Negative)) # Calculate sensitivity
    except ZeroDivisionError:  # Catch the divide by zero error
        Sensitivity = 0
    try:
        Specificity = (True_Negative / (True_Negative + False_Positive)) # Calculate specificity
    except ZeroDivisionError:
        Specificity
    try:
        Accuracy = (True_Positive + True_Negative) / (True_Negative + True_Positive + False_Positive + False_Negative) # Calculate accuracy
    except ZeroDivisionError:
        Accuracy = 0
    TPR = Sensitivity  # Calculate the true positive rate
    FPR = 1 - Specificity  # Calculate the false positive rate
    # Create a row to add to the compare_stocks
    add_row = {'Company' : Company, 'Days_Observed' : Days_Observed, 'Crosses' : Crosses, 'True_Positive' : True_Positive, 'False_Positive' : False_Positive, 
    'True_Negative' : True_Negative, 'False_Negative' : False_Negative, 'Sensitivity' : Sensitivity, 'Specificity' : Specificity, 'Accuracy' : Accuracy, 'TPR' : TPR, 'FPR' : FPR} 
    Compare_Stocks = Compare_Stocks.append(add_row, ignore_index = True) # Add the analysis on the stock to the existing Compare_Stocks dataframe
    count += 1
Compare_Stocks.to_csv("<Your Path>\\SMA_Analysis\\All_Stocks.csv", index = False)  # Save the compiled data on each stock to a csv - All_Stocks.csv