File size: 4,004 Bytes
4f94489
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1a80cf5
0aa4237
4f94489
 
 
 
 
 
 
 
0aa4237
4f94489
 
f9a8db6
 
1a80cf5
4f94489
0aa4237
4f94489
 
 
 
 
 
0aa4237
4f94489
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
788db71
 
 
 
 
 
 
 
 
 
 
4f94489
 
 
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
import pandas as pd
import gradio as gr
import plotly.express as px
import matplotlib.pyplot as plt
from wordcloud import WordCloud
from sklearn.feature_extraction.text import TfidfVectorizer
import numpy as np
from sklearn.feature_extraction.text import ENGLISH_STOP_WORDS

# words to remove
months = [
    "january",
    "february",
    "march",
    "april",
    "may",
    "june",
    "july",
    "august",
    "september",
    "october",
    "november",
    "december",
]
years = ["2024", "2025"]
filter_words = []
filter_words.extend(months)
filter_words.extend(years)


def plot_top_10_ranking_by_nr_trades(market_metrics: pd.DataFrame) -> gr.Plot:
    market_metrics_sorted_by_trades = market_metrics.sort_values(
        by="nr_trades", ascending=False
    )
    top_10_markets = market_metrics_sorted_by_trades.head(10)

    # Create a hover text column that combines market and nr_trades
    top_10_markets["hover_text"] = (
        top_10_markets["title"]
        + "<br>Number of Traders: "
        + top_10_markets["total_traders"].astype(str)
    )

    fig = px.bar(
        top_10_markets,
        x="market_id",
        y="nr_trades",
        hover_data=["hover_text"],
        title="Ranking of Markets by Number of Trades",
    )

    fig.update_layout(
        xaxis_title="Markets",
        yaxis_title="Number of Trades",
        xaxis={"showticklabels": False},
    )

    return gr.Plot(
        value=fig,
    )


def plot_trades_and_traders_ranking(market_metrics: pd.DataFrame) -> gr.Plot:
    print("plotting trades and traders scatterplot")
    ranking_fig = px.scatter(
        market_metrics,
        x="total_traders",
        y="nr_trades",
        color="nr_trades",
        color_continuous_scale="viridis",
        custom_data=["title"],
    )

    ranking_fig.update_layout(
        xaxis_title="Total Number of Traders",
        yaxis_title="Total Number of Trades",
        width=1000,  # Adjusted for better fit on laptop screens
        height=600,  # Adjusted for better fit on laptop screens
        # margin=dict(l=50, r=50, t=70, b=50),  # Adjust margins for better spacing
    )
    ranking_fig.update_traces(
        hovertemplate="Title: %{customdata[0]}<br>"
        + "Nr trades: %{y}<br>"
        + "Total traders: %{x}<br>",
    )

    return gr.Plot(
        value=ranking_fig,
    )


def plot_wordcloud_topics(market_metrics: pd.DataFrame) -> gr.Plot:
    # Sort the data by 'nr_trades' in descending order
    market_metrics_sorted = market_metrics.sort_values(by="nr_trades", ascending=False)
    # Get the titles of the top 100 markets
    top_100_titles = market_metrics_sorted["title"].head(100)
    # Combine standard English stop words with custom filter words
    all_stop_words = list(set(ENGLISH_STOP_WORDS).union(filter_words))

    # Create and configure TF-IDF Vectorizer
    tfidf = TfidfVectorizer(
        stop_words=all_stop_words, max_features=100, max_df=0.95, min_df=1
    )
    # Fit and transform the titles
    tfidf_matrix = tfidf.fit_transform(top_100_titles)

    # Get feature names (terms)
    terms = tfidf.get_feature_names_out()
    # Calculate average TF-IDF scores for each term
    avg_scores = np.mean(tfidf_matrix.toarray(), axis=0)
    word_scores = dict(zip(terms, avg_scores))

    # Create and generate a word cloud
    wordcloud = WordCloud(
        width=800,
        height=400,
        background_color="white",
        max_words=50,
        prefer_horizontal=0.7,
    ).generate_from_frequencies(word_scores)

    # Display the word cloud
    fig = plt.figure(figsize=(10, 5))
    ax = fig.add_subplot(111)

    # Plot wordcloud using the axes object
    ax.imshow(wordcloud, interpolation="bilinear")
    ax.axis("off")
    ax.set_title("Word Cloud of Market Titles")
    # plt.imshow(wordcloud, interpolation="bilinear")
    # plt.axis("off")
    # plt.title("Word Cloud of Market Titles")
    # # Close the figure to prevent memory leaks
    # plt.close()
    return gr.Plot(
        value=fig,
    )