File size: 8,704 Bytes
1da1c98
 
 
 
 
 
d3021f0
1da1c98
 
 
 
 
b1fc4cc
1da1c98
 
 
 
 
 
 
 
 
 
d3021f0
1da1c98
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b1fc4cc
1da1c98
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b1fc4cc
1da1c98
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b1fc4cc
1da1c98
 
 
 
b1fc4cc
1da1c98
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b1fc4cc
1da1c98
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import os
import scholarpy
import pandas as pd
import streamlit as st
import leafmap.foliumap as leafmap
import plotly.express as px
from leafmap.common import temp_file_path

if "dsl" not in st.session_state:
    st.session_state["dsl"] = scholarpy.Dsl()


@st.cache_data
def get_geonames():
    return scholarpy.get_geonames()


def json_to_df(json_data, transpose=False):
    df = json_data.as_dataframe()
    if not df.empty:
        if transpose:
            df = df.transpose()

        out_csv = temp_file_path(".csv")
        df.to_csv(out_csv, index=transpose)
        df = pd.read_csv(out_csv)
        os.remove(out_csv)
        return df
    else:
        return None


def annual_pubs(pubs, col="year"):
    if pubs is not None:
        df = pubs[col].value_counts().sort_index()
        df2 = pd.DataFrame({"year": df.index, "publications": df.values})
        return df2
    else:
        return None


def annual_collaborators(pubs, col="year"):
    if pubs is not None:
        df = pubs.groupby([col]).sum()
        df2 = pd.DataFrame(
            {"year": df.index, "collaborators": df["authors_count"].values}
        )
        fig = px.bar(
            df2,
            x="year",
            y="collaborators",
        )
        return fig
    else:
        return None


def annual_citations(pubs, col="year"):
    if pubs is not None:
        df = pubs.groupby([col]).sum()
        df2 = pd.DataFrame({"year": df.index, "citations": df["times_cited"].values})
        fig = px.bar(
            df2,
            x="year",
            y="citations",
        )
        return fig
    else:
        return None


def the_H_function(sorted_citations_list, n=1):
    """from a list of integers [n1, n2 ..] representing publications citations,
    return the max list-position which is >= integer

    eg
    >>> the_H_function([10, 8, 5, 4, 3]) => 4
    >>> the_H_function([25, 8, 5, 3, 3]) => 3
    >>> the_H_function([1000, 20]) => 2
    """
    if sorted_citations_list and sorted_citations_list[0] >= n:
        return the_H_function(sorted_citations_list[1:], n + 1)
    else:
        return n - 1


def app():

    st.title("Search Researchers")
    dsl = st.session_state["dsl"]
    row1_col1, row1_col2 = st.columns([1, 1])

    with row1_col1:
        name = st.text_input("Enter a researcher name:", "")

    if name:

        ids, names = dsl.search_researcher_by_name(name, return_list=True)
        if ids.count_total > 0:
            # options = ids.as_dataframe()["id"].values.tolist()
            with row1_col1:
                name = st.selectbox("Select a researcher id:", names)

            if name:
                id = name.split("|")[1].strip()
                id_info = dsl.search_researcher_by_id(id, return_df=False)

                info_df = json_to_df(id_info, transpose=True)
                info_df.rename(
                    columns={info_df.columns[0]: "Type", info_df.columns[1]: "Value"},
                    inplace=True,
                )
                with row1_col1:
                    st.header("Researcher Information")
                    if not info_df.empty:
                        st.dataframe(info_df)
                        leafmap.st_download_button(
                            "Download data", info_df, csv_sep="\t"
                        )
                    else:
                        st.text("No information found")

                pubs = dsl.search_pubs_by_researcher_id(id)
                df = json_to_df(pubs)
                # annual_df = annual_pubs(df)
                if df is not None:
                    df1, df2 = dsl.researcher_annual_stats(
                        pubs, geonames_df=get_geonames()
                    )
                    df3 = scholarpy.collaborator_locations(df2)

                    with row1_col2:
                        st.header("Researcher statistics")
                        columns = ["pubs", "collaborators", "institutions", "cities"]
                        selected_columns = st.multiselect(
                            "Select attributes to display:", columns, columns
                        )
                        if selected_columns:
                            fig = scholarpy.annual_stats_barplot(df1, selected_columns)
                            st.plotly_chart(fig)
                        leafmap.st_download_button(
                            "Download data",
                            df1,
                            file_name="data.csv",
                            csv_sep="\t",
                        )

                        st.header("Map of collaborator institutions")
                        markdown = f"""
                        - Total number of collaborator institutions: **{len(df3)}**
                        """
                        st.markdown(markdown)
                        m = leafmap.Map(
                            center=[0, 0],
                            zoom_start=1,
                            latlon_control=False,
                            draw_control=False,
                            measure_control=False,
                            locate_control=True,
                        )
                        m.add_points_from_xy(df3)
                        m.to_streamlit(height=420)
                        leafmap.st_download_button(
                            "Download data",
                            df3,
                            file_name="data.csv",
                            csv_sep="\t",
                        )

                        st.header("Publication counts with collaborators")
                        collaborators = dsl.search_researcher_collaborators(id, pubs)
                        markdown = f"""
                        - Total number of collaborators: **{len(collaborators)}**
                        """
                        st.markdown(markdown)
                        st.dataframe(collaborators)
                        leafmap.st_download_button(
                            "Download data",
                            collaborators,
                            file_name="data.csv",
                            csv_sep="\t",
                        )
                else:
                    st.text("No publications found")

                with row1_col1:
                    st.header("Publications")
                    if df is not None:
                        citations = df["times_cited"].values.tolist()
                        citations.sort(reverse=True)
                        h_index = the_H_function(citations)
                        markdown = f"""
                        - Total number of publications: **{len(df)}**
                        - Total number of citations: **{df["times_cited"].sum()}**
                        - i10-index: **{len(df[df["times_cited"]>=10])}**
                        - h-index: **{h_index}**
                        """
                        st.markdown(markdown)
                        st.dataframe(df)
                        leafmap.st_download_button(
                            "Download data", df, file_name="data.csv", csv_sep="\t"
                        )

                        if "journal.title" in df.columns:
                            st.header("Publication counts by journal")
                            journals = df["journal.title"].value_counts()
                            summary = pd.DataFrame(
                                {"Journal": journals.index, "Count": journals}
                            ).reset_index(drop=True)
                            markdown = f"""
                            - Total number of journals: **{len(summary)}**
                            """
                            st.markdown(markdown)
                            st.dataframe(summary)
                            leafmap.st_download_button(
                                "Download data",
                                summary,
                                file_name="data.csv",
                                csv_sep="\t",
                            )
                        else:
                            st.text("No journal publications")

                    else:
                        st.text("No publications found")

                    grants = dsl.search_grants_by_researcher(id)
                    df = grants.as_dataframe()
                    if not df.empty:
                        st.header("Grants")
                        st.dataframe(df)
                        leafmap.st_download_button(
                            "Download data", df, file_name="data.csv", csv_sep="\t"
                        )
        else:
            st.text("No results found.")