remove env

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -10,4 +10,6 @@ wheels/
 .venv
 # Data files
 *.parquet
+*.csv
 
+.env

README.md

@@ -0,0 +1,12 @@
+---
+title: PennyStockShortBacktester
+emoji: 👁
+colorFrom: purple
+colorTo: green
+sdk: docker
+pinned: false
+---
+
+# Penny Stock Short Backtester
+This application analyzes penny stock gaps and backtests short strategies.
+

backtester.py

@@ -12,6 +12,7 @@ def run_backtest(
     end_date,
     max_trades_per_day,
     commission_amount=2.0,
+    include_high_spike=False,
 ):
     """
     Runs the backtest logic on the provided dataframe with given parameters.
@@ -43,8 +44,11 @@ def run_backtest(
         "marketsession_30min",
         "marketsession_60min",
         "marketsession_120min",
-        "marketsession_high",
+        # "marketsession_high",
     ]
+    
+    if include_high_spike:
+        ms_columns.append("marketsession_high")
 
     for current_date in dates:
         countertradesperday = 0

create_mock_data.py

@@ -35,7 +35,7 @@ def create_mock_data():
             )
 
     df = pd.DataFrame(rows)
-    filename = "marketsession_post_polygon_2020-01-01_2025-12-01.parquet_with_premarketvolume900K_marketcap1B.parquet"
+    filename = "marketsession_post_polygon_2020-01-01_2026-01-01.parquet_with_premarketvolume900K_marketcap1B.parquet"
     df.to_parquet(filename)
     print(f"Mock data created: {filename}")
 

dashboard.py

@@ -48,14 +48,24 @@ commission_amount_input = pn.widgets.FloatInput(
 
 # Date Range (default based on user script)
 default_start = pd.Timestamp("2024-10-07").date()
-default_end = pd.Timestamp("2025-12-01").date()  # Future date from user script
-date_range_input = pn.widgets.DateRangeSlider(
-    name="Date Range",
+default_end = pd.Timestamp("2026-01-01").date()  # Future date from user script
+
+start_date_input = pn.widgets.DatePicker(
+    name="Start Date",
+    value=default_start,
+    start=pd.Timestamp("2020-01-01").date(),
+    end=pd.Timestamp("2026-01-01").date(),
+)
+end_date_input = pn.widgets.DatePicker(
+    name="End Date",
+    value=default_end,
     start=pd.Timestamp("2020-01-01").date(),
     end=pd.Timestamp("2026-01-01").date(),
-    value=(default_start, default_end),
 )
 
+high_spike_checkbox = pn.widgets.Checkbox(name="Include High Spike (marketsession_high)", value=False)
+high_spike_text = pn.pane.Markdown("this is high spike", styles={'font-size': '0.9em', 'color': 'gray', 'margin-top': '-10px'})
+
 run_button = pn.widgets.Button(name="Run Backtest", button_type="primary")
 
 
@@ -85,7 +95,9 @@ def execute_backtest(event=None):
     init_cap = initial_capital_input.value
     max_trades = max_trades_input.value
     comm_amt = commission_amount_input.value
-    start_date, end_date = date_range_input.value
+    start_date = start_date_input.value
+    end_date = end_date_input.value
+    include_high = high_spike_checkbox.value
 
     trades_df = run_backtest(
         current_df,
@@ -97,6 +109,7 @@ def execute_backtest(event=None):
         end_date,
         max_trades,
         commission_amount=comm_amt,
+        include_high_spike=include_high,
     )
 
     if trades_df.empty:
@@ -154,6 +167,66 @@ def execute_backtest(event=None):
         yformatter="%.0f",
     )
 
+    # 1c. Monthly Performance
+    # We need to calculate monthly return %.
+    # Strategy: Group by Month.
+    # Monthly PnL = Sum(pnl)
+    # Monthly Return % = Monthly PnL / Start of Month Capital * 100
+    # Start of Month Capital can be approximated by:
+    #   First trade of month 'capital_net' - trade 'pnl' -> This is capital before the first trade of the month.
+    #   (Note: This neglects capital changes if there were no trades for a while, but it's a good approximation for active trading)
+
+    analysis_df["month"] = pd.to_datetime(analysis_df["date"]).dt.to_period("M")
+    monthly_stats = (
+        analysis_df.groupby("month")
+        .agg(
+            {
+                "pnl": "sum",
+                "pnl_gross": "sum",
+                "capital_net": "first",  # We'll adjust this
+                "pnl": "sum",  # Re-asserting sum
+            }
+        )
+        .reset_index()
+    )
+
+    # To get the true start capital for the month, we find the first trade of that month and subtract its PnL from its ending capital_net.
+    # A more robust way:
+    # For each month, find the first trade index.
+    monthly_data = []
+    for m in analysis_df["month"].unique():
+        month_trades = analysis_df[analysis_df["month"] == m]
+        if month_trades.empty:
+            continue
+        
+        first_trade = month_trades.iloc[0]
+        start_cap = first_trade["capital_net"] - first_trade["pnl"]
+        
+        total_pnl = month_trades["pnl"].sum()
+        return_pct = (total_pnl / start_cap * 100) if start_cap != 0 else 0
+        
+        monthly_data.append({
+            "month": str(m),
+            "pnl": total_pnl,
+            "return_pct": return_pct
+        })
+    
+    monthly_df = pd.DataFrame(monthly_data)
+
+    monthly_plot = monthly_df.hvplot.bar(
+        x="month",
+        y="return_pct",
+        title="Monthly Performance (%)",
+        ylabel="Return (%)",
+        xlabel="Month",
+        grid=True,
+        height=300,
+        responsive=True,
+        color="#9C27B0",
+        yformatter="%.1f%%",
+        rot=45,
+    ) if not monthly_df.empty else pn.pane.Markdown("No monthly data")
+
     # 2. Cumulative Commission
     comm_plot = analysis_df.hvplot.line(
         x="index",
@@ -245,6 +318,7 @@ def execute_backtest(event=None):
                 comm_plot,
                 capital_days_plot,
                 profit_days_plot,
+                monthly_plot,
             ),
         ),
         pn.Row(pnl_dist_plot, ticker_plot),
@@ -288,7 +362,10 @@ sidebar = pn.Column(
     initial_capital_input,
     max_trades_input,
     commission_amount_input,
-    date_range_input,
+    start_date_input,
+    end_date_input,
+    high_spike_checkbox,
+    high_spike_text,
     run_button,
     pn.layout.Divider(),
     "**Note**: Ensure `HF_TOKEN` is set in `.env` to download data.",