File size: 5,664 Bytes
bbf5d55
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
import os
import sys
import pandas as pd
import torch
import torch.nn as nn
from sklearn.preprocessing import StandardScaler, LabelEncoder
import json

sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))

base_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
orig_data_path = os.path.join(base_dir, 'data', 'orig_processed.parquet')
combined_data_path = os.path.join(base_dir, 'data', 'final_data.parquet')
resources_dir = os.path.join(base_dir, 'resources')
os.makedirs(resources_dir, exist_ok=True)

original_df = pd.read_parquet(orig_data_path)
combined_df = pd.read_parquet(combined_data_path)

for df in [original_df, combined_df]:
    df.sort_values(['Ticker', 'Date'], inplace=True)
    df.reset_index(drop=True, inplace=True)

def add_trend_label(df):
    df['Next_Close'] = df.groupby('Ticker')['Close'].shift(-1)
    df['Trend'] = (df['Next_Close'] > df['Close']).astype(int)
    df.dropna(subset=['Next_Close'], inplace=True)
    return df

original_df = add_trend_label(original_df)
combined_df = add_trend_label(combined_df)

le = LabelEncoder()
original_df['TickerID'] = le.fit_transform(original_df['Ticker'])
combined_df['TickerID'] = le.transform(combined_df['Ticker'])

num_cols = ['Open', 'High', 'Low', 'Close', 'Volume']
feature_cols = num_cols + ['TickerID']
target_col = 'Trend'

original_df = original_df.sort_values(['TickerID', 'Date']).reset_index(drop=True)
combined_df = combined_df.sort_values(['TickerID', 'Date']).reset_index(drop=True)

X_orig = original_df[feature_cols]
y_orig = original_df[target_col]
X_mix = combined_df[feature_cols]
y_mix = combined_df[target_col]

split_idx = int(len(X_orig) * 0.8)
split_idx_mix = int(len(X_mix) * 0.8)

X_train_orig, X_test = X_orig.iloc[:split_idx].copy(), X_orig.iloc[split_idx:].copy()
y_train_orig, y_test = y_orig.iloc[:split_idx].copy(), y_orig.iloc[split_idx:].copy()

X_train_mix, _ = X_mix.iloc[:split_idx_mix].copy(), X_mix.iloc[split_idx_mix:].copy()
y_train_mix, _ = y_mix.iloc[:split_idx_mix].copy(), y_mix.iloc[split_idx_mix:].copy()

scaler = StandardScaler()
scaler.fit(X_train_orig[num_cols])

X_train_orig.loc[:, num_cols] = scaler.transform(X_train_orig[num_cols])
X_train_mix.loc[:, num_cols] = scaler.transform(X_train_mix[num_cols])
X_test.loc[:, num_cols] = scaler.transform(X_test[num_cols])

def to_tensor(X, y):
    X_num = torch.tensor(X[num_cols].values, dtype=torch.float32)
    X_ticker = torch.tensor(X['TickerID'].values, dtype=torch.long)
    y = torch.tensor(y.values, dtype=torch.float32).view(-1, 1)
    return X_num, X_ticker, y

X_train_orig_num, X_train_orig_ticker, y_train_orig_t = to_tensor(X_train_orig, y_train_orig)
X_train_mix_num, X_train_mix_ticker, y_train_mix_t = to_tensor(X_train_mix, y_train_mix)
X_test_num, X_test_ticker, y_test_t = to_tensor(X_test, y_test)

n_tickers_total = max(
    X_train_orig_ticker.max().item(),
    X_train_mix_ticker.max().item(),
    X_test_ticker.max().item()
) + 1

class TrendNN(nn.Module):
    def __init__(self, n_tickers, input_dim):
        super().__init__()
        self.ticker_embed = nn.Embedding(n_tickers, 8)
        self.net = nn.Sequential(
            nn.Linear(input_dim + 8, 64),
            nn.ReLU(),
            nn.Linear(64, 32),
            nn.ReLU(),
            nn.Linear(32, 1),
            nn.Sigmoid()
        )

    def forward(self, x_num, ticker_id):
        ticker_vec = self.ticker_embed(ticker_id)
        x = torch.cat([x_num, ticker_vec], dim=1)
        return self.net(x)

def train_model(X_num, X_ticker, y, X_val, X_val_ticker, y_val, name, epochs=100, batch_size=1024):
    model = TrendNN(n_tickers=n_tickers_total, input_dim=len(num_cols))
    criterion = nn.BCELoss()
    optimizer = torch.optim.Adam(model.parameters(), lr=0.001)

    history = {"train_loss": [], "val_loss": [], "val_acc": []}
    n_samples = len(X_num)

    for epoch in range(epochs):
        model.train()
        perm = torch.randperm(n_samples)
        total_loss = 0

        for i in range(0, n_samples, batch_size):
            idx = perm[i:i+batch_size]
            batch_X_num, batch_ticker, batch_y = X_num[idx], X_ticker[idx], y[idx]

            optimizer.zero_grad()
            y_pred = model(batch_X_num, batch_ticker)
            loss = criterion(y_pred, batch_y)
            loss.backward()
            optimizer.step()
            total_loss += loss.item()

        model.eval()
        with torch.no_grad():
            y_val_pred = model(X_val, X_val_ticker)
            val_loss = criterion(y_val_pred, y_val).item()
            val_acc = ((y_val_pred > 0.5).float() == y_val).float().mean().item()

        avg_train_loss = total_loss / (n_samples // batch_size)
        history["train_loss"].append(avg_train_loss)
        history["val_loss"].append(val_loss)
        history["val_acc"].append(val_acc)

        if (epoch + 1) % 5 == 0:
            print(f"[{name}] Epoch {epoch+1}/{epochs} | "
                  f"Train Loss: {avg_train_loss:.4f} | Val Loss: {val_loss:.4f} | Val Acc: {val_acc:.4f}")

    model_path = os.path.join(resources_dir, f"model_{name.lower()}.pt")
    torch.save(model.state_dict(), model_path)
    return model, history

model_orig, hist_orig = train_model(
    X_train_orig_num, X_train_orig_ticker, y_train_orig_t,
    X_test_num, X_test_ticker, y_test_t, "Original"
)

model_mix, hist_mix = train_model(
    X_train_mix_num, X_train_mix_ticker, y_train_mix_t,
    X_test_num, X_test_ticker, y_test_t, "Combined"
)

results = {
    "original": hist_orig,
    "combined": hist_mix
}
with open(os.path.join(resources_dir, 'training_metrics.json'), "w") as f:
    json.dump(results, f, indent=4)