File size: 5,236 Bytes
eb03925
 
0629e69
eb03925
0629e69
eb03925
 
0629e69
eb03925
 
 
 
0629e69
 
 
 
 
 
eb03925
 
 
 
0629e69
eb03925
 
 
 
 
 
 
 
 
0629e69
eb03925
 
0629e69
eb03925
0629e69
 
 
 
 
 
 
 
 
eb03925
0629e69
 
eb03925
 
 
 
 
0629e69
 
 
 
 
 
 
 
 
 
 
 
 
 
eb03925
 
0629e69
eb03925
0629e69
 
eb03925
 
 
0629e69
eb03925
0629e69
eb03925
0629e69
 
 
 
eb03925
0629e69
eb03925
 
0629e69
eb03925
 
0629e69
eb03925
0629e69
eb03925
 
 
 
0629e69
eb03925
 
 
0629e69
 
eb03925
 
 
0629e69
 
 
 
 
 
 
eb03925
 
0629e69
 
eb03925
 
 
0629e69
 
 
eb03925
0629e69
eb03925
 
0629e69
 
 
 
eb03925
 
0629e69
eb03925
 
0629e69
eb03925
 
0629e69
eb03925
0629e69
eb03925
 
 
 
0629e69
eb03925
 
 
0629e69
eb03925
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import base64
import io
from collections import Counter

import pandas as pd
import plotly.express as px
import plotly.graph_objects as go


def flatten_list_column(data, column):
    """Flatten a column containing lists into individual values with counts."""
    # Flatten the lists into individual items
    flattened = [
        item
        for sublist in data[column]
        if isinstance(sublist, list)
        for item in sublist
    ]
    # Count occurrences
    value_counts = pd.Series(Counter(flattened))
    return value_counts


def create_distribution_plot(data, column):
    """Create a beautiful distribution plot using Plotly and convert to image."""
    try:
        # Check if the column contains lists
        if isinstance(data[column].iloc[0], list):
            print(f"Processing list column: {column}")
            value_counts = flatten_list_column(data, column)
        else:
            # Handle regular columns
            if data[column].dtype in ["int64", "float64"]:
                # Continuous data - use histogram
                fig = go.Figure()

                # Add histogram
                fig.add_trace(
                    go.Histogram(
                        x=data[column],
                        name="Count",
                        nbinsx=30,
                        marker=dict(
                            color="rgba(110, 68, 255, 0.7)",
                            line=dict(color="rgba(184, 146, 255, 1)", width=1),
                        ),
                    )
                )

            else:
                # Categorical data
                value_counts = data[column].value_counts()

        # For both list columns and categorical data
        if "value_counts" in locals():
            fig = go.Figure(
                [
                    go.Bar(
                        x=value_counts.index,
                        y=value_counts.values,
                        marker=dict(
                            color=value_counts.values,
                            colorscale=px.colors.sequential.Plotly3,
                        ),
                    )
                ]
            )

        # Common layout updates
        fig.update_layout(
            title=f"Distribution of {column}",
            xaxis_title=column,
            yaxis_title="Count",
            template="plotly_white",
            margin=dict(t=50, l=50, r=50, b=50),
            width=1200,
            height=800,
            showlegend=False,
        )

        # Rotate x-axis labels if needed
        if isinstance(data[column].iloc[0], list) or data[column].dtype not in [
            "int64",
            "float64",
        ]:
            fig.update_layout(xaxis_tickangle=-45)

        # Convert to PNG
        img_bytes = fig.to_image(format="png", scale=2.0)

        # Encode to base64
        img_base64 = base64.b64encode(img_bytes).decode()

        return img_base64

    except Exception as e:
        print(f"Error creating distribution plot for {column}: {str(e)}")
        raise e


def create_wordcloud(data, column):
    """Create a word cloud visualization."""
    import matplotlib.pyplot as plt
    from wordcloud import WordCloud

    try:
        # Handle list columns
        if isinstance(data[column].iloc[0], list):
            text = " ".join(
                [
                    " ".join(map(str, sublist))
                    for sublist in data[column]
                    if isinstance(sublist, list)
                ]
            )
        else:
            # Handle regular columns
            text = " ".join(data[column].astype(str))

        wordcloud = WordCloud(
            width=1200,
            height=800,
            background_color="white",
            colormap="plasma",
            max_words=100,
        ).generate(text)

        # Create matplotlib figure
        plt.figure(figsize=(10, 5))
        plt.imshow(wordcloud, interpolation="bilinear")
        plt.axis("off")
        plt.title(f"Word Cloud for {column}")

        # Save to bytes
        buf = io.BytesIO()
        plt.savefig(buf, format="png", bbox_inches="tight", dpi=300)
        plt.close()
        buf.seek(0)

        # Convert to base64
        img_base64 = base64.b64encode(buf.getvalue()).decode()

        return img_base64

    except Exception as e:
        print(f"Error creating word cloud for {column}: {str(e)}")
        raise e


def create_wordcloud(data, column):
    """Create a word cloud visualization."""
    import matplotlib.pyplot as plt
    from wordcloud import WordCloud

    # Generate word cloud
    text = " ".join(data[column].astype(str))
    wordcloud = WordCloud(
        width=800,
        height=400,
        background_color="white",
        colormap="plasma",
        max_words=100,
    ).generate(text)

    # Create matplotlib figure
    plt.figure(figsize=(10, 5))
    plt.imshow(wordcloud, interpolation="bilinear")
    plt.axis("off")
    plt.title(f"Word Cloud for {column}")

    # Save to bytes
    buf = io.BytesIO()
    plt.savefig(buf, format="png", bbox_inches="tight", dpi=300)
    plt.close()
    buf.seek(0)

    # Convert to base64
    img_base64 = base64.b64encode(buf.getvalue()).decode()

    return img_base64