File size: 7,148 Bytes
e07e1fe
 
 
 
83fe832
 
e07e1fe
 
 
83fe832
 
 
e07e1fe
 
83fe832
e07e1fe
83fe832
cb9c774
e07e1fe
83fe832
 
e07e1fe
 
83fe832
e07e1fe
cb9c774
 
 
 
 
 
 
 
 
 
 
 
83fe832
 
 
 
 
 
 
 
e07e1fe
83fe832
 
cb9c774
83fe832
 
 
 
 
cb9c774
83fe832
cb9c774
 
83fe832
cb9c774
83fe832
 
 
cb9c774
83fe832
cb9c774
83fe832
 
 
cb9c774
 
 
83fe832
 
 
 
 
 
 
cb9c774
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
83fe832
 
 
 
cb9c774
83fe832
 
 
 
cb9c774
 
83fe832
 
 
 
 
 
 
 
cb9c774
83fe832
cb9c774
 
 
 
 
 
 
 
83fe832
 
e07e1fe
 
83fe832
 
 
 
 
 
 
 
 
 
cb9c774
 
 
 
 
 
 
 
e07e1fe
 
cb9c774
83fe832
 
 
cb9c774
 
83fe832
cb9c774
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e07e1fe
cb9c774
 
 
 
 
 
 
 
e07e1fe
83fe832
 
 
cb9c774
 
 
e07e1fe
cb9c774
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
83fe832
cb9c774
83fe832
cb9c774
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e07e1fe
83fe832
 
cb9c774
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
import gradio as gr
from datasets import load_dataset
import pandas as pd

# Datasets to include
DATASETS = {
    "CS1": "withmartian/cs1_dataset",
    "CS2": "withmartian/cs2_dataset",
    "CS3": "withmartian/cs3_dataset",
    "CS2 Synonyms": "withmartian/cs2_dataset_synonyms",
    "CS3 Synonyms": "withmartian/cs3_dataset_synonyms",
    "CS4 Synonyms": "withmartian/cs4_dataset_synonyms",
}

COLUMNS = ["create_statement", "english_prompt", "sql_statement"]

def load_preview(dataset_name):
    """Load first 500 rows of selected dataset"""
    try:
        ds = load_dataset(DATASETS[dataset_name], split="train")
        df = pd.DataFrame(ds)[COLUMNS].head(500)
        return df
    except Exception as e:
        return pd.DataFrame({"Error": [str(e)]})

def filter_dataframe(df, search_query):
    """Filter dataframe by search query across all columns"""
    if not search_query or df.empty or "Error" in df.columns:
        return df
    
    mask = df.astype(str).apply(
        lambda row: row.str.contains(search_query, case=False, na=False).any(), 
        axis=1
    )
    return df[mask]

# CSS styling
custom_css = """
:root {
    --martian-orange: #FF6B4A;
    --martian-black: #0A0A0A;
    --martian-gray-dark: #1A1A1A;
    --martian-gray-medium: #2A2A2A;
    --martian-gray-light: #3A3A3A;
}

.gradio-container {
    font-family: 'Inter', -apple-system, BlinkMacSystemFont, sans-serif;
    background-color: var(--martian-black) !important;
    color: #E0E0E0 !important;
}

.header-section {
    text-align: center;
    padding: 2.5rem 1.5rem;
    background: linear-gradient(135deg, var(--martian-gray-dark) 0%, var(--martian-gray-medium) 100%);
    border-radius: 16px;
    margin-bottom: 2rem;
    color: white;
    box-shadow: 0 4px 6px rgba(0,0,0,0.3);
}

.header-section h1 {
    font-size: 2.2rem;
    font-weight: 700;
    margin-bottom: 0.75rem;
}

.header-section .subtitle {
    font-size: 1.1rem;
    opacity: 0.9;
    line-height: 1.6;
}

.orange-accent {
    color: var(--martian-orange);
    font-weight: 600;
}

.info-box {
    background: var(--martian-gray-dark);
    border-radius: 12px;
    padding: 1.5rem;
    margin: 1.5rem 0;
    border-left: 4px solid var(--martian-orange);
    color: #E0E0E0;
}

.dataset-guide {
    background: var(--martian-gray-dark);
    border-radius: 8px;
    padding: 1rem;
    margin-top: 1rem;
    font-size: 0.9rem;
    color: #D0D0D0;
}

button.primary {
    background: var(--martian-orange) !important;
    border: none !important;
    color: white !important;
    font-weight: 600 !important;
}

button.primary:hover {
    background: #FF5733 !important;
    transform: translateY(-1px);
    box-shadow: 0 4px 8px rgba(255, 107, 74, 0.3);
}

input, select, textarea {
    background: var(--martian-gray-medium) !important;
    border-color: var(--martian-gray-light) !important;
    color: #E0E0E0 !important;
}

.dataframe {
    background: var(--martian-gray-dark) !important;
}

label {
    color: #D0D0D0 !important;
}

.label-wrap span {
    color: var(--martian-orange) !important;
}
"""

def dataset_viewer():
    with gr.Blocks(css=custom_css, title="TinySQL Dataset Viewer") as viewer:
        # Header
        gr.HTML("""
            <div class="header-section">
                <h1>TinySQL Dataset Viewer</h1>
                <p class="subtitle">
                    Browse dataset previews, search, and filter queries with <span class="orange-accent">ease</span>
                </p>
            </div>
        """)
        
        # Info box
        gr.HTML("""
            <div class="info-box">
                <strong>Preview Mode:</strong> Showing first 500 rows of each dataset. Use search to filter results in real-time.
            </div>
        """)
        
        with gr.Row():
            with gr.Column(scale=1):
                gr.Markdown("### Dataset Selection")
                dataset_dropdown = gr.Dropdown(
                    choices=list(DATASETS.keys()),
                    value="CS1",
                    label="Choose Dataset",
                    info="Select a dataset to preview"
                )
                
                gr.HTML("""
                    <div class="dataset-guide">
                        <strong>Complexity Levels:</strong><br><br>
                        <strong>CS1:</strong> Basic SELECT-FROM<br>
                        <strong>CS2:</strong> Adds ORDER BY<br>
                        <strong>CS3:</strong> Aggregations<br>
                        <strong>CS4:</strong> Adds WHERE filters<br><br>
                        <strong>Synonyms:</strong> Natural language variations
                    </div>
                """)
                
                load_btn = gr.Button("Load Dataset", variant="primary", size="lg")
                
                gr.HTML("<br>")
                
                demo_btn = gr.Button("πŸš€ Try Model Demo", variant="primary")
            
            with gr.Column(scale=3):
                gr.Markdown("### Dataset Preview (First 500 Rows)")
                
                search_box = gr.Textbox(
                    label="Search",
                    placeholder="Search across all columns...",
                    lines=1
                )
                
                df_display = gr.Dataframe(
                    headers=COLUMNS,
                    datatype=["str", "str", "str"],
                    interactive=False,
                    wrap=True,
                    max_rows=20,
                    label="Results"
                )
                
                stats_display = gr.Markdown("Click 'Load Dataset' to begin")
        
        # Store the loaded dataframe
        df_state = gr.State(value=pd.DataFrame())
        
        # Load dataset
        def load_and_display(dataset_name):
            df = load_preview(dataset_name)
            if "Error" in df.columns:
                return df, df, "❌ Error loading dataset"
            stats = f"**Loaded:** {len(df)} rows | **Columns:** {', '.join(COLUMNS)}"
            return df, df, stats
        
        load_btn.click(
            fn=load_and_display,
            inputs=dataset_dropdown,
            outputs=[df_state, df_display, stats_display]
        )
        
        # Search functionality
        def search_and_display(df, query):
            if df.empty:
                return df, "Load a dataset first"
            
            filtered_df = filter_dataframe(df, query)
            stats = f"**Showing:** {len(filtered_df)} of {len(df)} rows"
            if query:
                stats += f" | **Search:** '{query}'"
            return filtered_df, stats
        
        search_box.change(
            fn=search_and_display,
            inputs=[df_state, search_box],
            outputs=[df_display, stats_display]
        )
        
        # Open model demo
        demo_btn.click(
            lambda: None,
            None,
            None,
            _js="()=>{ window.open('https://huggingface.co/spaces/abir-hr196/tinysql-demo','_blank'); }"
        )
    
    return viewer

if __name__ == "__main__":
    dataset_viewer().launch()