Hugging Face's logo

Spaces:
jpwahle
/
field-diversity
Running

App Files Community
field-diversity
File size: 4,556 Bytes 
505fd08
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1380b5a
 
 
 
 
 
 
 
 
 
505fd08
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
# Copyright 2023 by Jan Philip Wahle, https://jpwahle.com/
# All rights reserved.

import os

import numpy as np
import pandas as pd
import seaborn as sns
from matplotlib import pyplot as plt
from scipy.stats import gaussian_kde

dirname = os.path.dirname(__file__)

# Load the csv file into a pandas DataFrame
papers_df = pd.read_csv(
    os.path.join(dirname, "data/nlp_papers_field_diversity.csv")
)

# Compute the mean CFDI
mean_cfdi = papers_df["incoming_diversity"].mean()

# Compute the mean CADI
mean_citation_ages = []

# Commenting out the old code
#|# Open the file and read the content in a list
#|with open(
#|    os.path.join(dirname, "data/nlp_papers_citation_age.txt"),
#|    "r",
#|    encoding="utf-8",
#|) as filehandle:
#|    for line in filehandle:
#|        temp = float(line[:-1])
#|        mean_citation_ages.append(temp)


def generate_cfdi_plot(input_cfdi, compute_type="paper"):
    """
    Function to generate a plot for CFDI
    """
    # Using kdeplot to fill the distribution curve
    sns.set(font_scale=1.3, style="whitegrid")

    data = papers_df[papers_df["incoming_diversity"] > 0]["incoming_diversity"]
    kde = gaussian_kde(data)
    x_vals = np.linspace(data.min(), data.max(), 1000)
    y_vals = kde.evaluate(x_vals)

    fig, ax = plt.subplots()  # create a new figure and axis

    ax.fill_between(x_vals, y_vals, color="skyblue", alpha=0.3)
    ax.plot(x_vals, y_vals, color="skyblue", linewidth=2, label="Distribution")

    interpolated_y_cfdi = np.interp(input_cfdi, x_vals, y_vals)
    ax.scatter(
        input_cfdi,
        interpolated_y_cfdi,
        c="r",
        marker="*",
        linewidths=2,
        zorder=2,
        s=32,
    )
    ax.vlines(
        input_cfdi,
        0,
        interpolated_y_cfdi,
        color="tomato",
        ls="--",
        lw=1.5,
    )

    epsilon = 0.005
    # Compute the average and plot it as a light grey vertical line
    mean_val = np.mean(data)
    # Interpolate the y value for the mean
    interpolated_y_mean = np.interp(mean_val, x_vals, y_vals)

    ax.vlines(mean_val, 0, interpolated_y_mean, color="grey", ls="--", lw=1.5)
    ax.text(
        mean_val + epsilon,
        interpolated_y_mean + epsilon,
        "Avg.",
        {"color": "grey", "fontsize": 13},
        ha="left",  # Horizontal alignment
    )
    ax.text(
        input_cfdi + epsilon,
        interpolated_y_cfdi + epsilon,
        f"This {compute_type}",
        {"color": "#DC143C", "fontsize": 13},
        ha="left",  # Horizontal alignment
    )

    ax.set_xlabel("Citation Field Diversity Index (CFDI)", fontsize=15)
    ax.set_ylabel("Density", fontsize=15)
    sns.despine(left=True, bottom=True, right=True, top=True)

    return fig


def generate_maoc_plot(input_maoc, compute_type="paper"):
    """
    Function to generate a plot for MAOC
    """
    # Using kdeplot to fill the distribution curve
    sns.set(font_scale=1.3, style="whitegrid")

    data = pd.DataFrame(mean_citation_ages)[0]
    kde = gaussian_kde(data)
    x_vals = np.linspace(data.min(), data.max(), 1000)
    y_vals = kde.evaluate(x_vals)

    fig, ax = plt.subplots()  # create a new figure and axis
    ax.fill_between(x_vals, y_vals, color="skyblue", alpha=0.3)
    ax.plot(x_vals, y_vals, color="skyblue", linewidth=2, label="Distribution")

    interpolated_y_cfdi = np.interp(input_maoc, x_vals, y_vals)
    ax.scatter(
        input_maoc,
        interpolated_y_cfdi,
        c="r",
        marker="*",
        linewidths=2,
        zorder=2,
        s=32,
    )
    ax.vlines(
        input_maoc,
        0,
        interpolated_y_cfdi,
        color="tomato",
        ls="--",
        lw=1.5,
    )

    epsilon = 0.005
    # Compute the average and plot it as a light grey vertical line
    mean_val = np.mean(data)
    # Interpolate the y value for the mean
    interpolated_y_mean = np.interp(mean_val, x_vals, y_vals)

    ax.vlines(mean_val, 0, interpolated_y_mean, color="grey", ls="--", lw=1.5)
    ax.text(
        mean_val + epsilon,
        interpolated_y_mean + epsilon,
        "Avg.",
        {"color": "grey", "fontsize": 13},
        ha="left",  # Horizontal alignment
    )
    ax.text(
        input_maoc + epsilon,
        interpolated_y_cfdi + epsilon,
        f"This {compute_type}",
        {"color": "#DC143C", "fontsize": 13},
        ha="left",  # Horizontal alignment
    )

    ax.set_xlabel("Mean Age of Citation (mAoC)", fontsize=15)
    ax.set_ylabel("Density", fontsize=15)
    sns.despine(left=True, bottom=True, right=True, top=True)

    return fig