Financial-Analysis-Python/preprocessing_data_for_ML.py at master · Samuel787/Financial-Analysis-Python · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
from collections import Counter
import numpy as np
import pandas as pd
import pickle
from sklearn import svm, neighbors
from sklearn.model_selection import cross_validate
from sklearn.model_selection import train_test_split
from sklearn.ensemble import VotingClassifier, RandomForestClassifier

def process_data_for_labels(ticker):
    hm_days = 7
    df = pd.read_csv('sp500_joined_closes.csv', index_col = 0)
    tickers = df.columns.values.tolist()
    df.fillna(0, inplace = True)

    for i in range(1, hm_days + 1):
        df['{}_{}d'.format(ticker, i)] = (df[ticker].shift(-i) -df[ticker]) / df[ticker]

    df.fillna(0, inplace = True)
    return tickers, df

#process_data_for_labels('AES')

def buy_sell_hold(*args):
    cols = [c for c in args]
    requirement = 0.02 #threshold -> tweak this number so that it is even btw buy, sell, hold
    for col in cols:
        if col > requirement:
            return 1
        if col < -requirement:
            return -1
    return 0

### extract feature sets and labels
def extract_featuresets(ticker):
    tickers, df = process_data_for_labels(ticker)
    df['{}_target'.format(ticker)] = list(map(
        buy_sell_hold,
        df['{}_1d'.format(ticker)],
        df['{}_2d'.format(ticker)],
        df['{}_3d'.format(ticker)],
        df['{}_4d'.format(ticker)],
        df['{}_5d'.format(ticker)],
        df['{}_6d'.format(ticker)],
        df['{}_7d'.format(ticker)]
    ))

    vals = df['{}_target'.format(ticker)].values.tolist()
    str_vals = [str(i) for i in vals]
    print("Data spread:", Counter(str_vals))

    df.fillna(0, inplace = True)
    df = df.replace([np.inf, -np.inf], np.nan)
    df.dropna(inplace = True)

    df_vals = df[[ticker for ticker in tickers]].pct_change()
    df_vals = df_vals.replace([np.inf, -np.inf], 0)
    df_vals.fillna(0, inplace = True)

    X = df_vals.values
    y = df['{}_target'.format(ticker)].values

    return X, y, df

def do_ml_kneighbour_classifier(ticker):
    X, y, df = extract_featuresets(ticker)
    X_train, X_test, y_train, y_test = train_test_split(
        X, y, test_size = 0.25
    )

    clf = neighbors.KNeighborsClassifier()

    clf.fit(X_train, y_train)
    confidence = clf.score(X_test, y_test)
    print("Accuracy", confidence)
    predictions = clf.predict(X_test)
    print("Predicted spread: ", Counter(predictions))

    return confidence

do_ml_kneighbour_classifier('AES')

def do_ml_voting_classifier(ticker):
    X, y, df = extract_featuresets(ticker)
    X_train, X_test, y_train, y_test = train_test_split(
        X, y, test_size = 0.25
    )

    clf = VotingClassifier(
        [
            ('lsvc', svm.LinearSVC()),
            ('knn', neighbors.KNeighborsClassifier()),
            ('rfor', RandomForestClassifier())
        ]
    )

    clf.fit(X_train, y_train)
    confidence = clf.score(X_test, y_test)
    print("Accuracy", confidence)
    predictions = clf.predict(X_test)
    print("Predicted spread: ", Counter(predictions))

    return confidence

do_ml_voting_classifier('ABT')