File size: 7,750 Bytes
3b89855
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9d85ec7
 
 
 
 
 
 
 
 
 
3b89855
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9d85ec7
 
 
 
3b89855
 
 
 
 
 
 
 
 
 
 
 
 
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
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
import gradio as gr
import numpy as np
import numexpr
import pandas as pd
import time


NUMEXPR_CONSTANTS = {
    'pi': np.pi,
    'PI': np.pi,
    'e': np.e,
}


def get_function(function, xlim=(-1, 1), nsample=100):
    x = np.linspace(xlim[0], xlim[1], nsample)
    y = numexpr.evaluate(function, local_dict={'x': x, **NUMEXPR_CONSTANTS})
    x = x.reshape(-1, 1)
    return x, y



def get_data_points(function, xlim=(-1, 1), nsample=10, sigma=0, seed=0):
    num_points_to_generate = 100
    if nsample > num_points_to_generate:
        raise ValueError(f"nsample too large, limit to {num_points_to_generate}")

    rng = np.random.default_rng(seed)
    x = rng.uniform(xlim[0], xlim[1], size=num_points_to_generate)
    x = x[:nsample]
    x = np.sort(x)

    rng = np.random.default_rng(seed)
    noise = sigma * rng.standard_normal(nsample)
    y = numexpr.evaluate(function, local_dict={'x': x, **NUMEXPR_CONSTANTS}) + noise

    x = x.reshape(-1, 1)
    return x, y


class Dataset:
    def __init__(
        self,
        mode: str = "generate",
        function: str = "sin(2 * pi * x)",
        xmin: float = -1.0,
        xmax: float = 1.0,
        nsample: int = 30,
        sigma: float = 0.0,
        seed: int = 0,
        csv_path: str = None,
    ):
        self.mode = mode

        self.function = function
        self.xmin = xmin
        self.xmax = xmax
        self.nsample = nsample
        self.sigma = sigma
        self.seed = seed

        self.csv_path = csv_path

        self.x, self.y = self._get_data()

    def _get_data(self):
        if self.mode == "generate":
            return get_data_points(
                function=self.function,
                xlim=(self.xmin, self.xmax),
                nsample=self.nsample,
                sigma=self.sigma,
                seed=self.seed,
            )

        elif self.mode == "csv":
            if self.csv_path is None:
                return np.array([]), np.array([])

            df = pd.read_csv(self.csv_path)
            if df.shape[1] != 2:
                raise ValueError("CSV file must have exactly two columns")

            x = df.iloc[:, 0].values.reshape(-1, 1)
            y = df.iloc[:, 1].values
            return x, y

        else:
            raise ValueError(f"Unknown dataset mode: {self.mode}")

    def update(self, **kwargs):
        return Dataset(
            mode=kwargs.get("mode", self.mode),
            function=kwargs.get("function", self.function),
            xmin=kwargs.get("xmin", self.xmin),
            xmax=kwargs.get("xmax", self.xmax),
            nsample=kwargs.get("nsample", self.nsample),
            sigma=kwargs.get("sigma", self.sigma),
            seed=kwargs.get("seed", self.seed),
            csv_path=kwargs.get("csv_path", self.csv_path),
        )

    def _safe_hash(self, val: int) -> int | tuple[int, str]:
        # special handling for -1 (same hash number as -2)
        if val == -1:
            return (-1, "special")
        return val

    def __hash__(self):
        return hash(
            (
                self.mode,
                self.function,
                self._safe_hash(self.xmin),
                self._safe_hash(self.xmax),
                self.nsample,
                self.sigma,
                self.seed,
                self.csv_path,
            )
        )


class DatasetView:
    def update_mode(self, mode: str, state: gr.State):
        state = state.update(mode=mode)

        if mode == "generate":
            return (
                state,
                gr.update(visible=True),  # function
                gr.update(visible=True),  # xmin
                gr.update(visible=True),  # xmax 
                gr.update(visible=True),  # sigma
                gr.update(visible=True),  # nsample
                gr.update(visible=True),  # regenerate
                gr.update(visible=False),  # csv upload
            )
        elif mode == "csv":
            return (
                state,
                gr.update(visible=False),  # function
                gr.update(visible=False),  # xmin
                gr.update(visible=False),  # xmax 
                gr.update(visible=False),  # sigma
                gr.update(visible=False),  # nsample
                gr.update(visible=False),  # regenerate
                gr.update(visible=True),  # csv upload
            )
        else:
            raise ValueError(f"Unknown mode: {mode}")

    def upload_csv(self, file, state):
        try:
            state = state.update(
                mode="csv",
                csv_path=file.name,
            )

        except Exception as e:
            gr.Info(f"⚠️   {e}")

        return state

    def regenerate_data(self, state: gr.State):
        seed = int(time.time() * 1000) % (2 ** 32)
        state = state.update(seed=seed)
        return state

    def update_all(self, function, xmin, xmax, sigma, nsample, state):
        state = state.update(
            function=function,
            xmin=xmin,
            xmax=xmax,
            sigma=sigma,
            nsample=nsample,
        )
        return state

    def build(self, state: gr.State):
        options = state.value

        with gr.Column():
            mode = gr.Radio(
                label="Dataset",
                choices=["generate", "csv"],
                value="generate",
            )

            function = gr.Textbox(
                label="Function (in terms of x)", 
                value=options.function,
            )
            with gr.Row():
                xmin = gr.Number(
                    label="x min", 
                    value=options.xmin,
                )
                xmax = gr.Number(
                    label="x max", 
                    value=options.xmax,
                )
            sigma = gr.Number(
                label="Gaussian noise standard deviation",
                value=options.sigma,
            )
            nsample = gr.Slider(
                label="Number of samples", 
                minimum=0, 
                maximum=100, 
                step=1, 
                value=options.nsample,
            )
            regenerate = gr.Button("Regenerate Data")

            csv_upload = gr.File(
                label="Upload CSV file", 
                file_types=['.csv'],
                visible=False,  # function mode is default
            )

        mode.change(
            fn=self.update_mode,
            inputs=[mode, state],
            outputs=[state, function, xmin, xmax, sigma, nsample, regenerate, csv_upload],
        )

        # generate mode
        function.submit(
            lambda f, s: s.update(function=f),
            inputs=[function, state],
            outputs=[state],
        )
        xmin.submit(
            lambda xmn, s: s.update(xmin=xmn),
            inputs=[xmin, state],
            outputs=[state],
        )
        xmax.submit(
            lambda xmx, s: s.update(xmax=xmx),
            inputs=[xmax, state],
            outputs=[state],
        )
        sigma.submit(
            lambda sig, s: s.update(sigma=sig),
            inputs=[sigma, state],
            outputs=[state],
        )
        nsample.change(
            lambda n, s: s.update(nsample=n),
            inputs=[nsample, state],
            outputs=[state],
        )
        regenerate.click(
            self.update_all,
            inputs=[function, xmin, xmax, sigma, nsample, state],
            outputs=[state],
        ).then(
            fn=self.regenerate_data,
            inputs=[state],
            outputs=[state],
        )

        # csv mode
        csv_upload.upload(
            self.upload_csv,
            inputs=[csv_upload, state],
            outputs=[state],
        )