Update app.py

app.py

@@ -1,151 +1,110 @@
-from pathlib import Path
-from typing import List, Dict, Tuple
-import matplotlib.colors as mpl_colors
-
 import pandas as pd
-import seaborn as sns
-import shinyswatch
-
-from shiny import App, Inputs, Outputs, Session, reactive, render, req, ui
-
-sns.set_theme()
-
-www_dir = Path(__file__).parent.resolve() / "www"
-
-df = pd.read_csv(Path(__file__).parent / "penguins.csv", na_values="NA")
-numeric_cols: List[str] = df.select_dtypes(include=["float64"]).columns.tolist()
-species: List[str] = df["Species"].unique().tolist()
-species.sort()
-
-app_ui = ui.page_fillable(
-    shinyswatch.theme.minty(),
-    ui.layout_sidebar(
-        ui.sidebar(
-            # Artwork by @allison_horst
-            ui.input_selectize(
-                "xvar",
-                "X variable",
-                numeric_cols,
-                selected="Bill Length (mm)",
-            ),
-            ui.input_selectize(
-                "yvar",
-                "Y variable",
-                numeric_cols,
-                selected="Bill Depth (mm)",
-            ),
-            ui.input_checkbox_group(
-                "species", "Filter by species", species, selected=species
-            ),
-            ui.hr(),
-            ui.input_switch("by_species", "Show species", value=True),
-            ui.input_switch("show_margins", "Show marginal plots", value=True),
-        ),
-        ui.output_ui("value_boxes"),
-        ui.output_plot("scatter", fill=True),
-        ui.help_text(
-            "Artwork by ",
-            ui.a("@allison_horst", href="https://twitter.com/allison_horst"),
-            class_="text-end",
-        ),
-    ),
-)
-
-
-def server(input: Inputs, output: Outputs, session: Session):
-    @reactive.Calc
-    def filtered_df() -> pd.DataFrame:
-        """Returns a Pandas data frame that includes only the desired rows"""
-
-        # This calculation "req"uires that at least one species is selected
-        req(len(input.species()) > 0)
-
-        # Filter the rows so we only include the desired species
-        return df[df["Species"].isin(input.species())]
-
-    @output
-    @render.plot
-    def scatter():
-        """Generates a plot for Shiny to display to the user"""
-
-        # The plotting function to use depends on whether margins are desired
-        plotfunc = sns.jointplot if input.show_margins() else sns.scatterplot
-
-        plotfunc(
-            data=filtered_df(),
-            x=input.xvar(),
-            y=input.yvar(),
-            palette=palette,
-            hue="Species" if input.by_species() else None,
-            hue_order=species,
-            legend=False,
-        )
-
-    @output
-    @render.ui
-    def value_boxes():
-        df = filtered_df()
-
-        def penguin_value_box(title: str, count: int, bgcol: str, showcase_img: str):
-            return ui.value_box(
-                title,
-                count,
-                {"class_": "pt-1 pb-0"},
-                showcase=ui.fill.as_fill_item(
-                    ui.tags.img(
-                        {"style": "object-fit:contain;"},
-                        src=showcase_img,
-                    )
-                ),
-                theme_color=None,
-                style=f"background-color: {bgcol};",
-            )
-
-        if not input.by_species():
-            return penguin_value_box(
-                "Penguins",
-                len(df.index),
-                bg_palette["default"],
-                # Artwork by @allison_horst
-                showcase_img="penguins.png",
-            )
-
-        value_boxes = [
-            penguin_value_box(
-                name,
-                len(df[df["Species"] == name]),
-                bg_palette[name],
-                # Artwork by @allison_horst
-                showcase_img=f"{name}.png",
-            )
-            for name in species
-            # Only include boxes for _selected_ species
-            if name in input.species()
-        ]
-
-        return ui.layout_column_wrap(*value_boxes, width = 1 / len(value_boxes))
-
-
-# "darkorange", "purple", "cyan4"
-colors = [[255, 140, 0], [160, 32, 240], [0, 139, 139]]
-colors = [(r / 255.0, g / 255.0, b / 255.0) for r, g, b in colors]
-
-palette: Dict[str, Tuple[float, float, float]] = {
-    "Adelie": colors[0],
-    "Chinstrap": colors[1],
-    "Gentoo": colors[2],
-    "default": sns.color_palette()[0],  # type: ignore
-}
-
-bg_palette = {}
-# Use `sns.set_style("whitegrid")` to help find approx alpha value
-for name, col in palette.items():
-    # Adjusted n_colors until `axe` accessibility did not complain about color contrast
-    bg_palette[name] = mpl_colors.to_hex(sns.light_palette(col, n_colors=7)[1])  # type: ignore
-
-
-app = App(
-    app_ui,
-    server,
-    static_assets=str(www_dir),
+import numpy as np
+import matplotlib.pyplot as plt
+from scipy.interpolate import interp1d
+from shiny import render
+from shiny.express import input, output, ui
+from utils import (
+    generate_2d_sequence,
+    plot_seq_full_label
 )
+import os
+import matplotlib as mpl
+import seaborn as sns
+mpl.rcParams.update(mpl.rcParamsDefault)
+
+df_gene_varient = pd.read_parquet("gene_varient.parquet")
+df_histone = pd.read_parquet("histone.parquet")
+df_gene_len = len(df_gene_varient)
+df_histone_len = len(df_histone)
+df_enhancer_annotation = pd.read_parquet('enhancer_annotation.parquet')
+df_enhancer_annotation_len = len(df_enhancer_annotation)
+ui.page_opts(fillable=True)
+
+with ui.navset_card_tab(id="tab"):
+    with ui.nav_panel("Gene Varient"):
+        ui.panel_title("Is there a pattern to gene varient location?")
+        with ui.layout_columns():
+            with ui.card():
+                ui.input_slider("sample", "sample", 0, df_gene_len, 40)
+                
+        def plot_loss_rates(df, sample, enhancer=False):
+            y_values = generate_2d_sequence(df['seq'].iloc[sample])[0]
+            x_values = generate_2d_sequence(df['seq'].iloc[sample])[1]
+            
+            integers = df['labels'].iloc[sample]
+            if enhancer:
+                K= 128
+                res = []
+                for i in integers:
+                    res.extend([i]*K)
+                integers = res
+            # Create a DataFrame with the x values, y values, and integers
+            data = {'x': x_values, 'y': y_values, 'color': integers}
+
+            # fig, ax = plt.subplots()
+
+
+            # Create a figure and axis
+            fig, ax = plt.subplots()
+            
+            # Create the scatter plot
+            scatter = ax.scatter(data['x'], data['y'], c=data['color'], cmap='tab20', s=0.5)
+            
+            # Add a colorbar
+            cbar = fig.colorbar(scatter, ax=ax)
+            cbar.set_label('Label')
+            
+            # Set labels and title
+            # ax.set_xlabel('X')
+            # ax.set_ylabel('Y')
+            # ax.set_title(f"Loss ra")
+            # ax.set_xlabel("Training steps")
+            # ax.set_ylabel("Loss rate")
+            return fig
+
+        @render.plot()
+        def plot_context_size_scaling():
+            fig = plot_loss_rates(df_gene_varient,input.sample() )
+            if fig:
+                return fig
+    with ui.nav_panel("Histone Modification"):
+        ui.panel_title("Is there a pattern to histone modification?")
+        with ui.layout_columns():
+            with ui.card():
+                ui.input_slider("sample_histone", "sample", 0, df_histone_len, 40)
+        
+        
+        def plot_histone(df,sample):
+            y_values = generate_2d_sequence(df['seq'].iloc[sample])[0]
+            x_values = generate_2d_sequence(df['seq'].iloc[sample])[1]
+            
+            integers = str((np.argwhere(df['labels'][sample] == np.amax(df['labels'][sample]))).flatten().tolist())
+            # Create a DataFrame with the x values, y values, and integers
+            data = {'x': x_values, 'y': y_values, 'color': integers}
+
+            fig, ax = plt.subplots()
+
+            sns.scatterplot(x='x', y='y', hue='color', data=data, palette='viridis', ax=ax)
+            ax.legend()
+            # ax.set_title(f"Loss ra")
+            # ax.set_xlabel("Training steps")
+            # ax.set_ylabel("Loss rate")
+            return fig      
+        @render.plot()
+        def plot_histones_two():
+            fig = plot_histone(df_histone,input.sample_histone() )
+            if fig:
+                return fig
+    with ui.nav_panel("Enhancer Annontations"):
+        ui.panel_title("Is there a pattern to enhancer annotations?")
+        with ui.layout_columns():
+            with ui.card():
+                ui.input_slider("sample_enhancer", "sample", 0, df_enhancer_annotation_len, 40)
+        @render.plot()
+        def plot_enhancer():
+            fig = plot_loss_rates(df_enhancer_annotation,input.sample_enhancer() , True)
+            if fig:
+                return fig            
+        
+