Custom Indicators matcher

indicators_matcher.py

import csv
import psycopg2

from difflib import SequenceMatcher
from tabulate import tabulate

MIN_SIMILARITY_RATIO = 0.8

# LOCAL
PSQL_HOST = 'localhost'
PSQL_PORT = '38036'
PSQL_USERNAME = 'magick'
PSQL_PASSWORD = 'magick'
PSQL_DBNAME = 'magick'

# Export to CSV -> https://docs.google.com/spreadsheets/d/1otjo4D8-_2twMQ8ppsJgx201sPPlcdPgDn6ghWRoDsI
CSV_PATH = '/Users/cristianmiranda/Desktop/custom_indicators.csv'

with open(CSV_PATH, 'rb') as f:
    reader = csv.reader(f)
    indicators = list(reader)

conn = psycopg2.connect(
    "dbname='{0}' user='{1}' host='{2}' port='{3}' password='{4}'"
        .format(PSQL_DBNAME, PSQL_USERNAME, PSQL_HOST, PSQL_PORT, PSQL_PASSWORD))
psql_cursor = conn.cursor()
psql_cursor.execute("select * from indicator_meta")
result = psql_cursor.fetchall()

indicators_map = {}

for row in result:
    db_indicator_name = row[1]

    for indicator in indicators:
        csv_indicator_name = indicator[1]
        csv_indicator_description = indicator[3]
        similarity_ratio = SequenceMatcher(None, db_indicator_name, csv_indicator_name).ratio()

        if (db_indicator_name not in indicators_map) or (similarity_ratio > indicators_map[db_indicator_name][0]):
            indicators_map[db_indicator_name] = {}
            indicators_map[db_indicator_name][0] = similarity_ratio
            indicators_map[db_indicator_name][1] = csv_indicator_name
            indicators_map[db_indicator_name][2] = csv_indicator_description

count = 0
values = []
for indicator in indicators_map:
    if indicators_map[indicator][0] > MIN_SIMILARITY_RATIO:
        percentage = "%.0f" % (indicators_map[indicator][0] * 100)
        values.append([percentage, indicator, indicators_map[indicator][1]])
        count += 1
        # print "UPDATE indicators_meta SET description = '%s' WHERE meta_type = '%s';" % (indicators_map[indicator][2], indicator)


print ""
print "- Similarity minimum ratio: %.2f" % MIN_SIMILARITY_RATIO
print "- DB Indicators : %d" % len(result)
print "- CSV Indicators : %d" % (len(indicators) - 1)
print "- Known indicators that can be updated: %d" % count
print "- Unknown indicators: %d" % (len(indicators) - 1 - count)
print ""
print tabulate(values, headers=['Similarity %', "DB Indicator", "CSV Indicator"])

• Similarity minimum ratio: 0.80
• DB Indicators : 91
• CSV Indicators : 219
• Known indicators that can be updated: 26
• Unknown indicators: 193

[Similarity %, DB Indicaror name, CSV Indicator name|

---

        97  KeltnerChannels        Keltner Channels
        84  LinearRegression       Linear Regression Line
        88  ComplexPairs           Complex_pairs
        95  TicksVolumeIndicator   Ticks Volume Indicator
        94  ATRMAOscillator        ATR MA Oscillator
        97  DynamicRS3CLines       DynamicRS_3CLines
        95  SolarWinds             Solar Winds
        88  SuperSignals           Super-signals
       100  BSpread                BSpread
        95  KlingerOscillatorKVO   Klinger Oscillator KVO
        92  FXFish                 FX Fish
        95  DojiArrows             Doji Arrows
       100  RSTL                   RSTL
        97  IntensivnostTikov      Intensivnost_Tikov
        95  CustomMACD             Custom MACD
        88  BollingerBands         Bollinger Bands %b
        84  Akurapopo              Aku Rapopo
        91  Sidus                  Sidus
        95  SignalBars             Signal Bars
        95  RelativeStrengthIndex  Relative Strength Index
        96  ComplexCommon          Complex_Common
        81  AwesomeOscillator      Ticker Awesome Oscillator
       100  MACD                   MACD
        89  MovingAverage          Moving Avreage
       100  NeuroProba             NeuroProba
        96  ParabolicSAR           Parabolic SAR