Taking a stab at converting a ThinkScript to Python for the first time, and I think my logic is right, but I am missing something as the two plots for the indicator don't match.
Trying to convert the ThinkScript for the VPNIndicator to a Python implementation. Looking for someone knowledgeable in both languages to contribute here.
To start, the indicator plot in ThinkorSwim looks like this (bottom):
So I'm trying to replicate that plot using matplotlib finance, but first I need to translate from ThinkScript to Python, which I've attempted here:
import mplfinance as mpf
import pandas as pd
import numpy as np
import talib
def VPN_Indicator(df, params):
# def atr = WildersAverage(TrueRange(high, close, low), length);
df['H-L'] = df['High'] - df['Low']
df['H-C1'] = df['High'] - df['Close'].shift()
df['C1-L'] = df['Close'].shift() - df['Low']
df['TrueRange'] = df[['H-L','H-C1','C1-L']].max(axis=1)
df['WildersATR'] = df['TrueRange'].ewm(alpha=1.0 / params['length'], adjust=False).mean()
# def diff = hlc3 - hlc3[1];
df['Diff'] = ((df['High'] + df['Low'] + df['Close']) / 3) - ((df['High'].shift() + df['Low'].shift() + df['Close'].shift()) / 3) # Forward peak here?
# def vp = Sum(if diff > factor * atr then volume else 0, length);
df['VP_Helper'] = np.where(df['Diff'] > params['factor'] * df['WildersATR'], df['Volume'], 0)
df['VP'] = df['VP_Helper'].rolling(params['length']).sum()
# def vn = Sum(if diff < -factor * atr then volume else 0, length);
df['VN_Helper'] = np.where(df['Diff'] < -params['factor'] * df['WildersATR'], df['Volume'], 0)
df['VN'] = df['VN_Helper'].rolling(params['length']).sum()
# plot VPN = ExpAverage(100 * (vp - vn) / Sum(volume, length), emaLength);
df['RollingVol'] = df['Volume'].rolling(params['length']).sum()
df['VPN'] = talib.EMA(100 * (df['VP'] - df['VN']) / df['RollingVol'], timeperiod=params['emaLength'])
# plot VPNAvg = MovingAverage(averageType, VPN, averageLength);
if params['averageType'] in ['simple','sma','SMA','SIMPLE']:
df['VPNAvg'] = talib.SMA(df['VPN'], timeperiod=params['averageLength'])
# plot CriticalLevel = criticalValue;
df['CriticalLevel'] = params['criticalValue']
# VPN.DefineColor("Above", Color.UPTICK);
# VPN.DefineColor("Below", Color.DOWNTICK);
# VPN.AssignValueColor(if VPN > CriticalLevel then VPN.Color("Above") else VPN.Color("Below"));
# VPNAvg.SetDefaultColor(GetColor(7));
# CriticalLevel.SetDefaultColor(GetColor(1));
# Gimicks, don't need the top bit for now
return df
params = {
"length": 30,
"emaLength": 3,
"averageLength": 30,
"factor": 0.1,
"criticalValue": 10,
"averageType": "simple"
}
# Import a 1min dataset and rename columns as necessary
df = pd.read_csv("SPY.csv").iloc[-2000:,:]
df['time'] = pd.to_datetime(df['time'])
df = df.set_index('time')
df = df.rename(columns={'open':'Open', 'high':'High', 'low':"Low", "close": "Close", "volume": "Volume"})
df = VPN_Indicator(df, params)
# Plot the results
apds = [ mpf.make_addplot((df['CriticalLevel']), panel=2, color='g'),
mpf.make_addplot((df['VPN']), panel=2, color='g'),
mpf.make_addplot((df['VPNAvg']), panel=2, color='g'),
]
mpf.plot(df[['Open', 'High', 'Low', 'Close', 'Volume']], addplot=apds, figscale=1.2, volume=True)
... which results in a plot that looks like this:
... which is close, but the peaks don't line up with the ThinkOrSwim plot. So I'm wanting to know from someone who knows these languages where I might be off? Thanks!
Try using this to calculate ATR. This gives the same output as TOS.
import numpy as np
def ema(arr, periods=14, weight=1, init=None):
leading_na = np.where(~np.isnan(arr))[0][0]
arr = arr[leading_na:]
alpha = weight / (periods + (weight-1))
alpha_rev = 1 - alpha
n = arr.shape[0]
pows = alpha_rev**(np.arange(n+1))
out1 = np.array([])
if 0 in pows:
out1 = ema(arr[:int(len(arr)/2)], periods)
arr = arr[int(len(arr)/2) - 1:]
init = out1[-1]
n = arr.shape[0]
pows = alpha_rev**(np.arange(n+1))
scale_arr = 1/pows[:-1]
if init:
offset = init * pows[1:]
else:
offset = arr[0]*pows[1:]
pw0 = alpha*alpha_rev**(n-1)
mult = arr*pw0*scale_arr
cumsums = mult.cumsum()
out = offset + cumsums*scale_arr[::-1]
out = out[1:] if len(out1) > 0 else out
out = np.concatenate([out1, out])
out[:periods] = np.nan
out = np.concatenate(([np.nan]*leading_na, out))
return out
def atr(highs, lows, closes, periods=14, ema_weight=1):
hi = np.array(highs)
lo = np.array(lows)
c = np.array(closes)
tr = np.vstack([np.abs(hi[1:]-c[:-1]),
np.abs(lo[1:]-c[:-1]),
(hi-lo)[1:]]).max(axis=0)
atr = ema(tr, periods=periods, weight=ema_weight)
atr = np.concatenate([[np.nan], atr])
return atr
Related
I am trying to calculate RSI using simple functions.
The general formula for it is:
RSI = 100/(1+RS), where RS = Exponential Moving Average of gains / -||- of losses.
Here is what I am getting:
enter image description here
Here it is how should it look like:
enter image description here
I have everything double checked or even triple checked, but I can't find any mistake.
Thus I need your help, I know that the question is very simple though I need some help, I have no idea where I have made the mistake.
The general idea of RSI is that it should be low where the price is "low" and high, where the price is high, and generally no matter what I try I have it upside down.
def EMA(close_price_arr, n):
a = (2/n + 1)
EMA_n = np.empty((1, len(close_price_arr)))
for i in range(len(close_price_arr)):
if i < n:
# creating NaN values where it is impossible to calculate EMA to drop it later after connecting the whole database
EMA_n[0, i] = 'NaN'
if i >= n:
# Calaculating nominator and denominator of EMA
for j in range(n):
nominator_ema += close_price_arr[i - j] * a**(j)
denominator_ema += a**(j)
EMA_n[0, i] = nominator_ema / denominator_ema
nominator_ema = 0
denominator_ema = 0
return EMA_n
def gains(close_price_arr):
gain_arr = np.empty((len(close_price_arr) - 1))
for i in range(len(close_price_arr)):
if i == 0:
pass
if i >= 1:
if close_price_arr[i] > close_price_arr[i - 1]:
gain_arr[i - 1] = (close_price_arr[i] - close_price_arr[i-1])
else:
gain_arr[i - 1] = 0
return gain_arr
def losses(close_price_arr):
loss_arr = np.empty((len(close_price_arr) - 1))
for i in range(len(close_price_arr)):
if i == 0:
pass
if i >= 1:
if close_price_arr[i] < close_price_arr[i - 1]:
loss_arr[i - 1] = abs(close_price_arr[i] - close_price_arr[i - 1])
else:
loss_arr[i - 1] = 0
return loss_arr
def RSI(gain_arr, loss_arr, n):
EMA_u = EMA(gain_arr, n)
EMA_d = EMA(loss_arr, n)
EMA_diff = EMA_u / EMA_d
x,y = EMA_diff.shape
print(x, y)
RSI_n = np.empty((1, y))
for i in range(y):
if EMA_diff[0, i] == 'NaN':
RSI_n[0, i] = 'NaN'
print(i)
else:
RSI_n[0, i] = 100 / (1 + EMA_diff[0, i])
return RSI_n
#contextmanager
def show_complete_array():
oldoptions = np.get_printoptions()
np.set_printoptions(threshold=np.inf)
try:
yield
finally:
np.set_printoptions(**oldoptions)
np.set_printoptions(linewidth=3000)
pd.set_option('display.max_columns', None)
# Specyfying root folder, file folder and file
FILE = 'TVC_SILVER, 5.csv'
FOLDER = 'src'
PROJECT_ROOT_DIR = '.'
csv_path = os.path.join(PROJECT_ROOT_DIR, FOLDER, FILE)
# reading csv
price_data = pd.read_csv(csv_path, delimiter=',')
price_data_copy = price_data.copy()
price_data_nodate = price_data.copy().drop('time', axis=1)
price_data_np = price_data_nodate.to_numpy(dtype='float32')
close_price = price_data_np[:, 3]
EMA15 = EMA(close_price_arr=close_price, n=15)
EMA55 = EMA(close_price_arr=close_price, n=55)
gain = gains(close_price_arr=close_price)
loss = losses(close_price_arr=close_price)
RSI14 = RSI(gain_arr=gain, loss_arr=loss, n=14)
Try this:
"""dataset is a dataframe"""
def RSI(dataset, n=14):
delta = dataset.diff()
dUp, dDown = delta.copy(), delta.copy()
dUp[dUp < 0] = 0
dDown[dDown > 0] = 0
RolUp = pd.Series(dUp).rolling(window=n).mean()
RolDown = pd.Series(dDown).rolling(window=n).mean().abs()
RS = RolUp / RolDown
rsi= 100.0 - (100.0 / (1.0 + RS))
return rsi
I am quite new to python so please bear with me.
Currently, this is my code:
import pandas as pd
import statistics
import matplotlib.pyplot as plt
import math
from datetime import datetime
start_time = datetime.now()
gf = pd.read_csv(r"/Users/aaronhuang/Documents/Desktop/ffp/exfileCLEAN2.csv",
skiprows=[1])
bf = pd.read_csv(r"/Users/aaronhuang/Documents/Desktop/ffp/2SeconddatasetCLEAN.csv",
skiprows=[1])
df = (input("Which data set? "))
magnitudes = (df['Magnitude '].values)
times = df['Time '].values
average = statistics.mean(magnitudes)
sd = statistics.stdev(magnitudes)
below = sd * 3
class data_set:
def __init__(self, index):
self.mags = []
self.i = index
self.mid_time = df['Time '][index]
self.mid_mag = df['Magnitude '][index]
self.times = []
ran = 80
for ii in range(ran):
self.times.append(df['Time '][self.i + ii - ran / 2])
self.mags.append(df['Magnitude '][self.i + ii - ran / 2])
data = []
today = float(input("What is the range? "))
i = 0
while (i < len(df['Magnitude '])):
if (abs(df['Magnitude '][i]) <= (average - below)):
# check if neighbours
t = df['Time '][i]
tt = True
for d in range(len(data)):
if abs(t - data[d].mid_time) <= today:
# check if closer to center
if df['Magnitude '][i] < data[d].mid_mag:
data[d] = data_set(i)
print("here")
tt = False
break
if tt:
data.append(data_set(i))
i += 1
print("found values")
# graphing
height = 2 # Change this for number of columns
width = math.ceil(len(data) / height)
if width < 2:
width = 2
fig, axes = plt.subplots(width, height, figsize=(30, 30))
row = 0
col = 0
for i in range(len(data)):
axes[row][col].plot(data[i].times, data[i].mags)
col += 1
if col > height - 1:
col = 0
row += 1
plt.show()
end_time = datetime.now()
print('Duration: {}'.format(end_time - start_time))
Currently, the error produced is this:
/Users/aaronhuang/.conda/envs/EXTTEst/bin/python "/Users/aaronhuang/PycharmProjects/EXTTEst/Code sandbox.py"
Which data set? gf
Traceback (most recent call last):
File "/Users/aaronhuang/PycharmProjects/EXTTEst/Code sandbox.py", line 14, in <module>
magnitudes = int(df['Magnitude '].values)
TypeError: string indices must be integers
Process finished with exit code 1
I am trying to have the user be able to choose which file to access to perform the rest of the code on.
So if the user types gf I would like the code to access the first data file.
Any help would be appreciated. Thank you
Why not use an if-statement at the beginning? Try this:
instead of:
gf = pd.read_csv(r"/Users/aaronhuang/Documents/Desktop/ffp/exfileCLEAN2.csv",
skiprows=[1])
bf = pd.read_csv(r"/Users/aaronhuang/Documents/Desktop/ffp/2SeconddatasetCLEAN.csv",
skiprows=[1])
df = (input("Which data set? "))
Use this:
choice = input("Which data set? ")
if choice == "gf":
df = pd.read_csv(r"/Users/aaronhuang/Documents/Desktop/ffp/exfileCLEAN2.csv",
skiprows=[1])
elif choice == "bf":
df = pd.read_csv(r"/Users/aaronhuang/Documents/Desktop/ffp/2SeconddatasetCLEAN.csv",
skiprows=[1])
else:
print("Error. Your choice is not valid")
df = ""
break
I am working on some python code to predict Default rate of loans handed out by a bank.
I have calculated the WOE and information value (IV) on the training set
(using the following code: https://github.com/Sundar0989/WOE-and-IV/blob/master/WOE_IV.ipynb?fbclid=IwAR1MvEfyGsdyTre0uPJC5WRl91dfue_t0vH5qJezwm2mAg6sjHZJg9MyDYo).
We have also concluded 2 high cardinality variables. We don't know however how to add these WOE scores to the whole set. How do we tackle this problem? How can we go further to use WOE to predict the target variable?
code:
import os
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import scipy, pylab
Reading the data received from bank, feature selection part 1, splitting up whole set (Training) into training set: indices_traintrain, validation set: indices_val and test set: indices_test (70/30 split training and validation set - test set and 70/30 split training - validation)
Training =
pd.read_excel('/Users/enjo/Documents/Master/DM/Data_DSC2019_STUDENTS/DSC2019_Training.xlsx', na_values=np.nan)
Status = Training.iloc[:,-1]
Data = Training.iloc[:,0:45]
Data_missing = Data.isna()
Data_missing = Data_missing.sum()
print(Data_missing/len(Data))
"""
drop variables with more than 80% missing
"""
Drop = ['FREE_CASH_FLOW_AMT',
'A2_MTHS_FIRST_PCX_COREPROF_CNT', 'A2_MONTHS_IN_BELGIUM_CNT', 'A2_MTHS_SNC_FIRST_COREPROF_CNT', 'MONTHS_SINCE_LAST_REFUSAL_CNT']
DroppedTraining = Training.copy()
for element in Drop:
DroppedTraining.drop(element, axis=1,inplace=True)
import numpy as np
from sklearn import datasets
from sklearn import svm
from sklearn import preprocessing
Data_preprocessed=[] #contains preprocessed data
from Preprocessing_continuous import Preprocessing_continuous #import function for preprocessing
from Preprocessing_discrete import Preprocessing_discrete #import function for preprocessing
from sklearn.model_selection import train_test_split
indices=np.arange(26962)
indices_train, indices_test = train_test_split(indices, test_size=0.3, random_state=0)
indices_traintrain, indices_val = train_test_split(indices_train, test_size=0.3, random_state=0)
Training['target']= Training['Label_Default'].apply(lambda x:1 if x=='Y' else 0)
Highcardinalityset=[]
Highcardinalityset = Training[['Type',
'INDUSTRY_CD_3',
'INDUSTRY_CD_4',
'Managing_Sales_Office_Nbr',
'Postal_Code_L',
'Product_Desc',
'CREDIT_TYPE_CD',
'ACCOUNT_PURPOSE_CD',
'A2_MARITAL_STATUS_CD',
'FINANCIAL_PRODUCT_TYPE_CD',
'A2_EMPLOYMENT_STATUS_CD',
'A2_RESIDENT_STATUS_CD',
'target']]
Highcardinalityset = Highcardinalityset.iloc[indices_traintrain]
function found on github
import pandas as pd
import numpy as np
import pandas.core.algorithms as algos
from pandas import Series
import scipy.stats.stats as stats
import re
import traceback
import string
max_bin = 20
force_bin = 3
# define a binning function
def mono_bin(Y, X, n = max_bin):
df1 = pd.DataFrame({"X": X, "Y": Y})
justmiss = df1[['X','Y']][df1.X.isnull()]
notmiss = df1[['X','Y']][df1.X.notnull()]
r = 0
while np.abs(r) < 1:
try:
d1 = pd.DataFrame({"X": notmiss.X, "Y": notmiss.Y, "Bucket": pd.qcut(notmiss.X, n)})
d2 = d1.groupby('Bucket', as_index=True)
r, p = stats.spearmanr(d2.mean().X, d2.mean().Y)
n = n - 1
except Exception as e:
n = n - 1
if len(d2) == 1:
n = force_bin
bins = algos.quantile(notmiss.X, np.linspace(0, 1, n))
if len(np.unique(bins)) == 2:
bins = np.insert(bins, 0, 1)
bins[1] = bins[1]-(bins[1]/2)
d1 = pd.DataFrame({"X": notmiss.X, "Y": notmiss.Y, "Bucket": pd.cut(notmiss.X, np.unique(bins),include_lowest=True)})
d2 = d1.groupby('Bucket', as_index=True)
d3 = pd.DataFrame({},index=[])
d3["MIN_VALUE"] = d2.min().X
d3["MAX_VALUE"] = d2.max().X
d3["COUNT"] = d2.count().Y
d3["EVENT"] = d2.sum().Y
d3["NONEVENT"] = d2.count().Y - d2.sum().Y
d3=d3.reset_index(drop=True)
if len(justmiss.index) > 0:
d4 = pd.DataFrame({'MIN_VALUE':np.nan},index=[0])
d4["MAX_VALUE"] = np.nan
d4["COUNT"] = justmiss.count().Y
d4["EVENT"] = justmiss.sum().Y
d4["NONEVENT"] = justmiss.count().Y - justmiss.sum().Y
d3 = d3.append(d4,ignore_index=True)
d3["EVENT_RATE"] = d3.EVENT/d3.COUNT
d3["NON_EVENT_RATE"] = d3.NONEVENT/d3.COUNT
d3["DIST_EVENT"] = d3.EVENT/d3.sum().EVENT
d3["DIST_NON_EVENT"] = d3.NONEVENT/d3.sum().NONEVENT
d3["WOE"] = np.log(d3.DIST_EVENT/d3.DIST_NON_EVENT)
d3["IV"] = (d3.DIST_EVENT-d3.DIST_NON_EVENT)*np.log(d3.DIST_EVENT/d3.DIST_NON_EVENT)
d3["VAR_NAME"] = "VAR"
d3 = d3[['VAR_NAME','MIN_VALUE', 'MAX_VALUE', 'COUNT', 'EVENT', 'EVENT_RATE', 'NONEVENT', 'NON_EVENT_RATE', 'DIST_EVENT','DIST_NON_EVENT','WOE', 'IV']]
d3 = d3.replace([np.inf, -np.inf], 0)
d3.IV = d3.IV.sum()
return(d3)
def char_bin(Y, X):
df1 = pd.DataFrame({"X": X, "Y": Y})
justmiss = df1[['X','Y']][df1.X.isnull()]
notmiss = df1[['X','Y']][df1.X.notnull()]
df2 = notmiss.groupby('X',as_index=True)
d3 = pd.DataFrame({},index=[])
d3["COUNT"] = df2.count().Y
d3["MIN_VALUE"] = df2.sum().Y.index
d3["MAX_VALUE"] = d3["MIN_VALUE"]
d3["EVENT"] = df2.sum().Y
d3["NONEVENT"] = df2.count().Y - df2.sum().Y
if len(justmiss.index) > 0:
d4 = pd.DataFrame({'MIN_VALUE':np.nan},index=[0])
d4["MAX_VALUE"] = np.nan
d4["COUNT"] = justmiss.count().Y
d4["EVENT"] = justmiss.sum().Y
d4["NONEVENT"] = justmiss.count().Y - justmiss.sum().Y
d3 = d3.append(d4,ignore_index=True)
d3["EVENT_RATE"] = d3.EVENT/d3.COUNT
d3["NON_EVENT_RATE"] = d3.NONEVENT/d3.COUNT
d3["DIST_EVENT"] = d3.EVENT/d3.sum().EVENT
d3["DIST_NON_EVENT"] = d3.NONEVENT/d3.sum().NONEVENT
d3["WOE"] = np.log(d3.DIST_EVENT/d3.DIST_NON_EVENT)
d3["IV"] = (d3.DIST_EVENT-d3.DIST_NON_EVENT)*np.log(d3.DIST_EVENT/d3.DIST_NON_EVENT)
d3["VAR_NAME"] = "VAR"
d3 = d3[['VAR_NAME','MIN_VALUE', 'MAX_VALUE', 'COUNT', 'EVENT', 'EVENT_RATE', 'NONEVENT', 'NON_EVENT_RATE', 'DIST_EVENT','DIST_NON_EVENT','WOE', 'IV']]
d3 = d3.replace([np.inf, -np.inf], 0)
d3.IV = d3.IV.sum()
d3 = d3.reset_index(drop=True)
return(d3)
def data_vars(df1, target):
stack = traceback.extract_stack()
filename, lineno, function_name, code = stack[-2]
vars_name = re.compile(r'\((.*?)\).*$').search(code).groups()[0]
final = (re.findall(r"[\w']+", vars_name))[-1]
x = df1.dtypes.index
count = -1
for i in x:
if i.upper() not in (final.upper()):
if np.issubdtype(df1[i], np.number) and len(Series.unique(df1[i])) > 2:
conv = mono_bin(target, df1[i])
conv["VAR_NAME"] = i
count = count + 1
else:
conv = char_bin(target, df1[i])
conv["VAR_NAME"] = i
count = count + 1
if count == 0:
iv_df = conv
else:
iv_df = iv_df.append(conv,ignore_index=True)
iv = pd.DataFrame({'IV':iv_df.groupby('VAR_NAME').IV.max()})
iv = iv.reset_index()
return(iv_df,iv)
final_iv, IV = data_vars(Highcardinalityset,Highcardinalityset.target)
final_iv
IV.sort_values('IV')
IV.to_csv('test.csv')
transform_vars_list = Highcardinalityset.columns.difference(['target'])
transform_prefix = 'new_' # leave this value blank if you need replace the original column values
transform_vars_list
for var in transform_vars_list:
small_df = final_iv[final_iv['VAR_NAME'] == var]
transform_dict = dict(zip(small_df.MAX_VALUE.astype(str),small_df.WOE.astype(str)))
replace_cmd = ''
replace_cmd1 = ''
for i in sorted(transform_dict.items()):
replace_cmd = replace_cmd + str(i[1]) + str(' if x <= ') + str(i[0]) + ' else '
replace_cmd1 = replace_cmd1 + str(i[1]) + str(' if x == "') + str(i[0]) + '" else '
replace_cmd = replace_cmd + '0'
replace_cmd1 = replace_cmd1 + '0'
if replace_cmd != '0':
try:
Highcardinalityset[transform_prefix + var] = Highcardinalityset[var].apply(lambda x: eval(replace_cmd))
except:
Highcardinalityset[transform_prefix + var] = Highcardinalityset[var].apply(lambda x: eval(replace_cmd1))
Highcardinalityset['Postal_Code_L'].value_counts()
Highcardinalityset['new_Postal_Code_L'].value_counts()
Highcardinalityset['Managing_Sales_Office_Nbr'].value_counts()
Highcardinalityset['new_Managing_Sales_Office_Nbr'].value_counts()
Nice to see when high WOE: interesting for that postal code: high risk for default!
Highcardinalityset.to_excel("Highcardinalitysettraintrain.xlsx")
TrainingWOE = DroppedTraining[['Managing_Sales_Office_Nbr', "Postal_Code_L"]]
TrainingWOE["Postal_Code_L_WOE"]=Highcardinalityset[["new_Postal_Code_L"]]
TrainingWOE["Managing_Sales_Office_Nbr_WOE"]=Highcardinalityset[["new_Managing_Sales_Office_Nbr"]]
drop variables that are not relevant because of low IV value
Drop = ["ACCOUNT_PURPOSE_CD", "A2_MARITAL_STATUS_CD", "A2_EMPLOYMENT_STATUS_CD", "A2_RESIDENT_STATUS_CD",
"INDUSTRY_CD_3", "INDUSTRY_CD_4","Type"]
DroppedTrainingAfterIVcalc = DroppedTraining.copy()
for element in Drop:
DroppedTrainingAfterIVcalc.drop(element, axis=1,inplace=True)
preprocess remaining (44-5 (because of too many missing) - 7 (because of low iv) + 1 (target variable added))
Thanks for asking this question. Here is the code to do the required transformation which is shown in the notebook as well.
transform_vars_list = df.columns.difference(['target'])
transform_prefix = 'new_' # leave this value blank to replace the original column
#apply transformations
for var in transform_vars_list:
small_df = final_iv[final_iv['VAR_NAME'] == var]
transform_dict = dict(zip(small_df.MAX_VALUE,small_df.WOE))
replace_cmd = ''
replace_cmd1 = ''
for i in sorted(transform_dict.items()):
replace_cmd = replace_cmd + str(i[1]) + str(' if x <= ') + str(i[0]) + ' else '
replace_cmd1 = replace_cmd1 + str(i[1]) + str(' if x == "') + str(i[0]) + '" else '
replace_cmd = replace_cmd + '0'
replace_cmd1 = replace_cmd1 + '0'
if replace_cmd != '0':
try:
df[transform_prefix + var] = df[var].apply(lambda x: eval(replace_cmd))
except:
df[transform_prefix + var] = df[var].apply(lambda x: eval(replace_cmd1))
In addition, there is a package Xverse which does the same. Please refer to it here - https://github.com/Sundar0989/XuniVerse
Cost function implemented with Python:
**Thanks for help to achieve this.
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
load_data = pd.read_csv('C:\python_program\ex1data1.txt',sep = ",",header = None)
feature_vale = load_data[0]
y = np.matrix(load_data[1])
m = len(feature_vale)
plt.scatter(load_data[0],load_data[1],marker='+',c = 'r')
plt.title("Cost_Function")
plt.xlabel("Population of City in 10,000s")
plt.ylabel("Profit in $10,000s")
df = pd.DataFrame(pd.Series(1,index= range(0,m)))
df[1] = load_data[0]
X = np.matrix(df)
row_theta = np.zeros(2,dtype = int)
theta = np.array([row_theta]) # Transpose the array
prediction = np.dot(X,theta.T)
error = (prediction-y.T)
error_df = pd.DataFrame(error)
#square the error
squared_error = np.square(error_df)
sum = np.sum(squared_error)
print(sum)
J = np.sum(squared_error) / (2 * m)
print(J)
Data reference link: searchcode.com/codesearch/view/5404318
repeat the following steps and let me know
load_data = pd.read_csv('data.txt',sep = ",",header = None)
feature_vale = load_data[0]
y = np.matrix(load_data[1])
m = len(feature_vale)
#print(m)
#plt.scatter(load_data[0],load_data[1])
df = pd.DataFrame(pd.Series(1,index= range(0,m)))
df[1] = load_data[0]
X = np.matrix(df)
row_theta = np.zeros(2,dtype = int)
theta = np.array([row_theta]) # Transpose the array
print(theta.T)
prediction = np.matmul(X,theta.T)
error = (prediction-y)
error_df = pd.DataFrame(error)
squared_error = np.square(error_df)
print(squared_error)
I know this is not an ideal place for questions of this scope, but I'm not sure where else to ask this or how to break it down. I've been working on a function for the past couple weeks, that runs, but for it to be feasible for my purposes, I need to speed it up 200-300x.
I have an image array, where all pixels of similar color have been averaged and set to that average value. Then I have a 2D array of the same height and width, which labels each unique and non-contiguous feature of the image.
Using these I need to assess the size of each feature and its level of contrast to each of its neighbors. These values are used in an equation and if the output of that equation is below a certain threshold, that feature is merged with its most similar neighbor.
I've uploaded the image and the feature label array (printed with numpy.savetext()) to OneDrive and attached links
code:
def textureRemover(pix, labeledPix, ratio = 1.0):
numElements = numpy.amax(labeledPix)
maxSize = numpy.count_nonzero(labeledPix)
MAXIMUMCONTRAST = 443.405
for regionID in range(numElements):
start = time.clock()
regionID += 1
if regionID not in labeledPix:
continue
#print(regionID)
#print((regionID / numElements) * 100, '%')
neighborIDs = getNeighbors(labeledPix, regionID)
if 0 in neighborIDs:
neighborIDs.remove(0) #remove white value
regionMask = labeledPix == regionID
region = pix[regionMask]
size = numpy.count_nonzero(regionMask)
contrastMin = (ratio - (size / maxSize)) * MAXIMUMCONTRAST
regionMean = region.mean(axis = 0)
if len(neighborIDs) > 200:
contrast = numpy.zeros(labeledPix.shape)
contrast[labeledPix!=0] = numpy.sqrt(numpy.sum((regionMean - pix[labeledPix!=0])**2, axis = -1))
significantMask = (contrast < contrastMin)
significantContrasts = list(numpy.unique(contrast[significantMask]))
significantNeighbors = {}
for significantContrast in significantContrasts:
minContrast = min(significantContrasts)
if labeledPix[contrast == minContrast][0] in neighborIDs:
significantNeighbors[minContrast] = labeledPix[contrast == minContrast][0]
else:
significantContrasts.pop(significantContrasts.index(minContrast))
else:
significantNeighbors = {}
for neighborID in neighborIDs:
neighborMask = labeledPix == neighborID
neighbor = pix[neighborMask]
neighborMean = neighbor.mean(axis = 0)
contrast = numpy.sqrt(numpy.sum((regionMean - neighborMean)**2, axis = -1))
if contrast < contrastMin:
significantNeighbors[contrast] = neighborID
if significantNeighbors:
contrasts = significantNeighbors.keys()
minContrast = min(contrasts)
minNeighbor = significantNeighbors[minContrast]
neighborMask = labeledPix == minNeighbor
neighborSize = numpy.count_nonzero(neighborMask)
if neighborSize <= size:
labeledPix[neighborMask] = regionID
pix[neighborMask] = regionMean
else:
labeledPix[regionMask] = minNeighbor
pix[regionMask] = pix[neighborMask].mean(axis = 0)
print(time.clock() - start)
return pix
pix
labeledPix
I know I'm asking for a lot of help, but I've been stuck on this for a few weeks and am unsure what else I can do. Any help will be greatly appreciated!
Here is an optimized version of most of your logic (I underestimated the amount of work that would be...). I skipped the >200 branch and am using fake data because I couldn't access your link. When I switch off your >200 branch your and my code appear to give the same result but mine is quite a bit faster on the fake example.
Sample output:
original
26.056154000000003
optimized
0.763613000000003
equal
True
Code:
import numpy as np
from numpy.lib.stride_tricks import as_strided
def mockdata(m, n, k):
colors = np.random.random((m, n, 3))
i, j = np.ogrid[:m, :n]
labels = np.round(k*k * (np.sin(0.05 * i) + np.sin(0.05 * j)**2)).astype(int) % k
return colors, labels
DIAG_NEIGHBORS = True
MAXIMUMCONTRAST = 443.405
def textureRemover2(pix, labeledPix, ratio=1.0):
start = time.clock()
pix, labeledPix = pix.copy(), labeledPix.copy()
pixf, labeledPixf = pix.reshape(-1, 3), labeledPix.ravel()
m, n = labeledPix.shape
s, t = labeledPix.strides
# find all sizes in O(n)
sizes = np.bincount(labeledPixf)
n_ids = len(sizes)
# make index for quick access to labeled areas
lblidx = np.split(np.argsort(labeledPixf), np.cumsum(sizes[:-1]))
lblidx[0] = None
# find all mean colors in O(n)
regionMeans = np.transpose([np.bincount(labeledPix.ravel(), px)
/ np.maximum(sizes, 1)
for px in pix.reshape(-1, 3).T])
# find all neighbors in O(n)
horz = set(frozenset(p) for bl in as_strided(labeledPix, (m,n-1,2), (s,t,t))
for p in bl)
vert = set(frozenset(p) for bl in as_strided(labeledPix, (m-1,n,2), (s,t,s))
for p in bl)
nb = horz|vert
if DIAG_NEIGHBORS:
dwnrgt = set(frozenset(p) for bl in as_strided(
labeledPix, (m-1,n-1,2), (s,t,s+t)) for p in bl)
dwnlft = set(frozenset(p) for bl in as_strided(
labeledPix[::-1], (m-1,n-1,2), (-s,t,t-s)) for p in bl)
nb = nb|dwnrgt|dwnlft
nb = {p for p in nb if len(p) == 2 and not 0 in p}
nb_dict = {}
for a, b in nb:
nb_dict.setdefault(a, set()).add(b)
nb_dict.setdefault(b, set()).add(a)
maxSize = labeledPix.size - sizes[0]
for id_ in range(1, n_ids):
nbs = list(nb_dict.get(id_, set()))
if not nbs:
continue
d = regionMeans[id_] - regionMeans[nbs]
d = np.einsum('ij,ij->i', d, d)
mnd = np.argmin(d)
if d[mnd] < ((ratio - sizes[id_]/maxSize) * MAXIMUMCONTRAST)**2:
mn = nbs[mnd]
lrg, sml = (id_, mn) if sizes[id_] >= sizes[mn] else (mn, id_)
sizes[lrg], sizes[sml] = sizes[lrg] + sizes[sml], 0
for nb in nb_dict[sml]:
nb_dict[nb].remove(sml)
nb_dict[nb].add(lrg)
nb_dict[lrg].update(nb_dict[sml])
nb_dict[lrg].remove(lrg)
nb_dict[sml] = set()
pixf[lblidx[sml]] = regionMeans[lrg]
labeledPixf[lblidx[sml]] = lrg
lblidx[lrg], lblidx[sml] = np.r_[lblidx[lrg],lblidx[sml]], None
print(time.clock() - start)
return pix
from scipy.ndimage.morphology import binary_dilation
import time
STRUCTEL = np.ones((3,3), int) if DIAG_NEIGHBORS else np.array([[0,1,0],[1,1,1],[0,1,0]], int)
def getNeighbors(labeledPix, regionID):
nb = set(labeledPix[binary_dilation(labeledPix == regionID, structure=STRUCTEL)])
nb.remove(regionID)
return sorted(nb)
numpy = np
def textureRemover(pix, labeledPix, ratio = 1.0):
pix, labeledPix = pix.copy(), labeledPix.copy()
numElements = numpy.amax(labeledPix)
maxSize = numpy.count_nonzero(labeledPix)
MAXIMUMCONTRAST = 443.405
start = time.clock()
for regionID in range(numElements):
regionID += 1
if regionID not in labeledPix:
continue
#print(regionID)
#print((regionID / numElements) * 100, '%')
neighborIDs = getNeighbors(labeledPix, regionID)
if 0 in neighborIDs:
neighborIDs.remove(0) #remove white value
regionMask = labeledPix == regionID
region = pix[regionMask]
size = numpy.count_nonzero(regionMask)
contrastMin = (ratio - (size / maxSize)) * MAXIMUMCONTRAST
regionMean = region.mean(axis = 0)
if len(neighborIDs) > 20000:
contrast = numpy.zeros(labeledPix.shape)
contrast[labeledPix!=0] = numpy.sqrt(numpy.sum((regionMean - pix[labeledPix!=0])**2, axis = -1))
significantMask = (contrast < contrastMin)
significantContrasts = list(numpy.unique(contrast[significantMask]))
significantNeighbors = {}
for significantContrast in significantContrasts:
minContrast = min(significantContrasts)
if labeledPix[contrast == minContrast][0] in neighborIDs:
significantNeighbors[minContrast] = labeledPix[contrast == minContrast][0]
else:
significantContrasts.pop(significantContrasts.index(minContrast))
else:
significantNeighbors = {}
for neighborID in neighborIDs:
neighborMask = labeledPix == neighborID
neighbor = pix[neighborMask]
neighborMean = neighbor.mean(axis = 0)
contrast = numpy.sqrt(numpy.sum((regionMean - neighborMean)**2, axis = -1))
if contrast < contrastMin:
significantNeighbors[contrast] = neighborID
if significantNeighbors:
contrasts = significantNeighbors.keys()
minContrast = min(contrasts)
minNeighbor = significantNeighbors[minContrast]
neighborMask = labeledPix == minNeighbor
neighborSize = numpy.count_nonzero(neighborMask)
if neighborSize <= size:
labeledPix[neighborMask] = regionID
pix[neighborMask] = regionMean
else:
labeledPix[regionMask] = minNeighbor
pix[regionMask] = pix[neighborMask].mean(axis = 0)
print(time.clock() - start)
return pix
data = mockdata(200, 200, 1000)
print('original')
res0 = textureRemover(*data)
print('optimized')
res2 = textureRemover2(*data)
print('equal')
print(np.allclose(res0, res2))