Last active
June 30, 2019 01:12
-
-
Save bharddwaj/1f9b2ab9f089c9a7066b66efc68e6976 to your computer and use it in GitHub Desktop.
finds the bid-ask spread for each row and records the frequency of each different spread and graphs them at the end. Used this for liquidity research on 64 million rows of data!
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
import numpy as np | |
import csv | |
import seaborn as sns | |
import matplotlib.pyplot as plt | |
import math | |
data = pd.read_csv("CL_June_2019.csv") | |
print(type(data)) | |
#new_data = data[59528000:59800000] | |
#print(new_data) | |
#new_data.to_csv("new_file.csv") | |
count = 0 | |
spread = [] | |
frequency = {} | |
spread.append( data['Bid Price']) | |
spread.append(data['Ask Price']) | |
for i in range(len(spread[0])): | |
count += 1 | |
bid = spread[0][i] | |
ask = spread[1][i] | |
if not math.isnan(bid) and not math.isnan(ask): | |
difference = round(abs(bid - ask),2) | |
print(difference) | |
if difference in frequency: | |
frequency[difference] += 1 | |
else: | |
frequency[difference] = 1 | |
print(count) | |
sns.barplot(x = [keys for keys in frequency],y = [frequency[keys] for keys in frequency]) | |
plt.xlabel("Spread") | |
plt.ylabel('Frequency') | |
plt.title(f"Bid-Ask Spread") | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment