File size: 12,820 Bytes
8cc7d1d
 
 
 
 
 
 
779436a
8cc7d1d
779436a
 
 
8cc7d1d
779436a
8cc7d1d
779436a
 
 
 
 
8cc7d1d
 
779436a
8cc7d1d
 
779436a
 
8cc7d1d
 
 
779436a
 
8cc7d1d
 
 
779436a
 
 
 
8cc7d1d
 
 
 
 
 
779436a
8cc7d1d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
779436a
8cc7d1d
 
779436a
8cc7d1d
 
 
 
779436a
8cc7d1d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
779436a
8cc7d1d
 
779436a
8cc7d1d
 
 
 
 
 
 
 
 
 
 
 
779436a
8cc7d1d
 
 
 
779436a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8cc7d1d
 
 
 
 
779436a
 
8cc7d1d
779436a
8cc7d1d
779436a
 
 
 
 
 
 
8cc7d1d
779436a
8cc7d1d
 
 
779436a
 
8cc7d1d
 
 
779436a
 
 
 
8cc7d1d
779436a
 
8cc7d1d
 
 
 
779436a
8cc7d1d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
779436a
8cc7d1d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
779436a
8cc7d1d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
779436a
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
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
import pandas as pd
import matplotlib.pyplot as plt
from collections import Counter
import matplotlib.ticker as ticker

def category_chart(file_path):
    # Load the Excel file
    df = pd.read_excel(file_path)

    # Ensure the 'Topic' column exists and drop any rows without a topic
    if 'Topic' not in df.columns or df['Topic'].isnull().all():
        raise ValueError("The 'Topic' column is missing or empty.")

    df.dropna(subset=['Topic'], inplace=True)

    # Split multiple topics and flatten the list
    all_topics = [topic.strip() for sublist in df['Topic'].str.split(',').tolist() for topic in sublist if topic]

    # Count occurrences of each topic
    topic_counts = Counter(all_topics)

    # Convert to DataFrame for plotting
    topic_counts_df = pd.DataFrame(topic_counts.items(), columns=['Topic', 'Count']).sort_values('Count', ascending=False)

    # Plotting
    plt.close('all')
    fig, ax = plt.subplots(figsize=(14, 7))
    ax.set_facecolor('#222c52')
    fig.patch.set_facecolor('#222c52')

    colors = ['#08F7FE' if i % 2 == 0 else '#FE53BB' for i in range(len(topic_counts_df))]
    topic_counts_df.plot(kind='bar', x='Topic', y='Count', ax=ax, color=colors, edgecolor=colors, alpha=0.7, linewidth=2, legend=None)

    ax.xaxis.label.set_color('white')
    ax.yaxis.label.set_color('white')
    ax.tick_params(axis='x', colors='white', labelsize=10, direction='out', length=6, width=2, rotation=45)
    ax.tick_params(axis='y', colors='white', labelsize=10, direction='out', length=6, width=2)
    ax.set_title('Topic Frequency Distribution', color='white', fontsize=16)
    ax.set_xlabel('Topic', fontsize=14)
    ax.set_ylabel('Count', fontsize=14)
    ax.grid(True, which='both', axis='y', color='gray', linestyle='-', linewidth=0.5, alpha=0.5)
    ax.set_axisbelow(True)

    for spine in ax.spines.values():
        spine.set_color('white')
        spine.set_linewidth(1)
    ax.spines['right'].set_visible(False)
    ax.spines['top'].set_visible(False)
    return fig




def status_chart(file_path):
    # Load the Excel file
    plt.close('all')
    data = pd.read_excel(file_path)

    # Calculate the frequency of each status
    status_counts = data['Status'].value_counts()

    # Define colors with 50% opacity
    colors = ['#08F7FE80', '#FE53BB80',
              '#fff236de', '#90ff00bf']  # '80' for 50% opacity

    # Plotting
    fig, ax = plt.subplots()
    fig.patch.set_facecolor('#222c52')  # Set the background color of the figure
    ax.set_facecolor('#222c52')  # Set the background color of the axes
    wedges, texts, autotexts = ax.pie(status_counts, autopct='%1.1f%%', startangle=90, colors=colors,
                                      wedgeprops=dict(edgecolor='white', linewidth=1.5))

    # Set legend
    ax.legend(wedges, status_counts.index, title="Document Status", loc="center left", bbox_to_anchor=(1, 0, 0.5, 1))

    ax.set_ylabel('')  # Remove the y-label
    ax.set_title('Document Status Distribution', color='white')

    plt.setp(autotexts, size=8, weight="bold", color="white")

    return fig



def plot_glowing_line_with_dots_enhanced(ax, x, y, color, label, glow_size=10, base_linewidth=3, markersize=8):
    for i in range(1, glow_size + 1):
        alpha_value = (1.0 / glow_size) * (i / (glow_size / 2))
        if alpha_value > 1.0:
            alpha_value = 1.0
        linewidth = base_linewidth * i * 0.5
        ax.plot(x, y, color=color, linewidth=linewidth, alpha=alpha_value * 0.1)
    ax.plot(x, y, color=color, linewidth=base_linewidth, marker='o', linestyle='-', label=label, markersize=markersize)

def company_document_type(file_path, company_names):
    plt.close('all')
    if isinstance(company_names, str):
        company_names = [name.strip() for name in company_names.split(',')]

    df = pd.read_excel(file_path)

    fig, ax = plt.subplots(figsize=(14, 8))
    ax.set_facecolor('#222c52')
    fig.patch.set_facecolor('#222c52')

    colors = ['#08F7FE', '#FE53BB', '#fff236']  # Add more colors if necessary

    max_count = 0
    for index, company_name in enumerate(company_names):
        df_company = df[df['Source'].str.contains(company_name, case=False, na=False)]
        document_counts = df_company['Type'].value_counts()
        all_document_types = df['Type'].unique()
        document_counts = document_counts.reindex(all_document_types, fill_value=0)

        x_data = document_counts.index
        y_data = document_counts.values
        ax.fill_between(x_data, y_data, -0.2, color=colors[index % len(colors)], alpha=0.1)
        plot_glowing_line_with_dots_enhanced(ax, x_data, y_data, colors[index % len(colors)], company_name, base_linewidth=4)

        if max_count < max(y_data):
            max_count = max(y_data)

    ax.set_xticks(range(len(all_document_types)))
    ax.set_xticklabels(all_document_types, rotation=45, fontsize=12, fontweight='bold', color='white')
    ax.yaxis.set_major_locator(ticker.MaxNLocator(integer=True))
    ax.set_ylabel('Count', color='white')
    ax.set_title('Document Types Contributed by Companies', color='white')
    ax.grid(True, which='both', axis='both', color='gray', linestyle='-', linewidth=0.5, alpha=0.5)
    ax.set_axisbelow(True)

    plt.ylim(-0.2, max_count + 1)

    for spine in ax.spines.values():
        spine.set_color('white')
        spine.set_linewidth(2)

    ax.spines['right'].set_visible(False)
    ax.spines['top'].set_visible(False)
    ax.spines['left'].set_position(('data', 0))
    plt.legend(facecolor='#222c52', edgecolor='white', fontsize=12, labelcolor='white')

    return fig


def get_expert(file_path):
    # Load the Excel file
    df = pd.read_excel(file_path)

    # Ensure the 'Expert' column exists
    if 'Expert' not in df.columns:
        raise ValueError("The 'Expert' column is missing from the provided file.")

    # Combine all the experts into a single list, accounting for multiple experts per row
    all_experts = []
    for experts in df['Expert'].dropna().unique():
        all_experts.extend([expert.strip() for expert in experts.split(',')])

    # Get unique experts and return them
    unique_experts = sorted(set(all_experts))
    return gr.update(choices=list(unique_experts))

def chart_by_expert(file_path, expert_name):
    plt.close('all')
    # Load the Excel file
    data = pd.read_excel(file_path)

    # Normalize the expert's name if it follows a specific format; otherwise, adjust accordingly
    parts = expert_name.split('/')
    name = parts[1].strip() if len(parts) > 1 else expert_name.strip()

    # Normalize function for companies, similar to the original code
    def normalize_companies(company_list, merge_entities):
        normalized = set()
        for company in company_list:
            normalized_name = merge_entities.get(company.strip(), company.strip())
            normalized.add(normalized_name)
        return list(normalized)

    # Define merge entities mapping, as provided
    merge_entities = {
        "Nokia Shanghai Bell": "Nokia",
        "Qualcomm Korea": "Qualcomm",
        # Add all other mappings as per the original code
        # ...
        "Hugues Network Systems": "Hughes"
    }

    # Adjust data processing to handle multiple experts and sources
    # Flatten and normalize the source field across relevant rows
    data['ExpertsList'] = data['Expert'].dropna().apply(lambda x: [expert.strip() for expert in x.split(',')])
    data_exploded = data.explode('ExpertsList')

    # Filter the data for the specified expert and handle multiple sources
    filtered_data = data_exploded[data_exploded['ExpertsList'].str.contains(name, case=False, na=False)]
    sources = filtered_data['Source'].dropna()
    split_sources = sources.apply(lambda x: normalize_companies(x.split(', '), merge_entities))
    all_sources = [company for sublist in split_sources for company in sublist]

    # Count occurrences and get the top 10
    source_counts = Counter(all_sources)
    top_10_sources = source_counts.most_common(10)

    # Convert to DataFrame for plotting
    top_10_df = pd.DataFrame(top_10_sources, columns=['Company', 'Count'])

    # Plotting
    fig, ax = plt.subplots(figsize=(14, 11))
    ax.set_facecolor('#222c52')
    fig.patch.set_facecolor('#222c52')

    # Alternating colors for the bars
    colors = ['#08F7FE' if i % 2 == 0 else '#FE53BB' for i in range(len(top_10_df))]
    top_10_df.plot(kind='bar', x='Company', y='Count', ax=ax, color=colors, edgecolor=colors, alpha=0.5, linewidth=5)

    # Set chart details
    ax.xaxis.label.set_color('white')
    ax.yaxis.label.set_color('white')
    ax.tick_params(axis='x', colors='white', labelsize=12, direction='out', length=6, width=2, rotation=45)
    ax.tick_params(axis='y', colors='white', labelsize=12, direction='out', length=6, width=2)
    ax.set_title(f"Top 10 Contributors for Expert '{expert_name}'", color='white', fontsize=16)
    ax.set_xlabel('Company', fontsize=14)
    ax.set_ylabel('Count', fontsize=14)
    ax.yaxis.set_major_locator(ticker.MaxNLocator(integer=True))
    ax.grid(True, which='both', axis='y', color='gray', linestyle='-', linewidth=0.5, alpha=0.5)
    ax.set_axisbelow(True)

    for spine in ax.spines.values():
        spine.set_color('white')
        spine.set_linewidth(2)
    ax.spines['right'].set_visible(False)
    ax.spines['top'].set_visible(False)

    return fig




# @title Top 10 des entreprises en termes de publications



def generate_company_chart(file_path):
    # plt.close('all')
    # Define merge entities mapping
    merge_entities = {
        "Nokia Shanghai Bell": "Nokia",
        "Qualcomm Korea": "Qualcomm",
        "Qualcomm Incorporated": "Qualcomm",
        "Huawei Technologies R&D UK": "Huawei",
        "Hughes Network Systems": "Hughes",
        "HUGHES Network Systems": "Hughes",
        "Hughes Network systems": "Hughes",
        "HUGHES Network Systems Ltd": "Hughes",
        "KT Corp.": "KT Corporation",
        "Deutsche Telekom AG": "Deutsche Telekom",
        "LG Electronics Inc.": "LG Electronics",
        "LG Uplus": "LG Electronics",
        "OPPO (chongqing) Intelligence": "OPPO",
        "Samsung Electronics GmbH": "Samsung",
        "China Mobile International Ltd": "China Mobile",
        "NOVAMINT": "Novamint",
        "Eutelsat": "Eutelsat Group",
        "Inmarsat Viasat": "Inmarsat",
        "China Telecommunications": "China Telecom",
        "SES S.A.": "SES",
        "Ericsson GmbH": "Ericsson",
        "JSAT": "SKY Perfect JSAT",
        "NEC Europe Ltd": "NEC",
        "Fraunhofer IIS": "Fraunhofer",
        "Hugues Network Systems": "Hughes"
    }

    # Function to normalize company names within each cell
    def normalize_companies(company_list, merge_entities):
        normalized = set()  # Use a set to avoid duplicates within the same cell
        for company in company_list:
            normalized_name = merge_entities.get(company.strip(), company.strip())
            normalized.add(normalized_name)
        return list(normalized)

    # Load the Excel file
    data = pd.read_excel(file_path)

    # Prepare the data
    sources = data['Source'].dropna()
    split_sources = sources.apply(lambda x: normalize_companies(x.split(', '), merge_entities))

    # Flatten the list of lists while applying the merge rules
    all_sources = [company for sublist in split_sources for company in sublist]

    # Count occurrences
    source_counts = Counter(all_sources)
    top_10_sources = source_counts.most_common(10)

    # Convert to DataFrame for plotting
    top_10_df = pd.DataFrame(top_10_sources, columns=['Company', 'Count'])

    # Plotting
    fig, ax = plt.subplots(figsize=(14, 12))
    ax.set_facecolor('#222c52')
    fig.patch.set_facecolor('#222c52')

    # Alternating colors for the bars
    colors = ['#08F7FE' if i % 2 == 0 else '#FE53BB' for i in range(len(top_10_df))]
    top_10_df.plot(kind='bar', x='Company', y='Count', ax=ax, color=colors, edgecolor=colors, alpha=0.5, linewidth=5, legend=None)

    # Set chart details
    ax.xaxis.label.set_color('white')
    ax.yaxis.label.set_color('white')
    ax.tick_params(axis='x', colors='white', labelsize=16, direction='out', length=6, width=2, rotation=37)
    ax.tick_params(axis='y', colors='white', labelsize=12, direction='out', length=6, width=2)
    ax.set_title('Top 10 Contributors: Ranking Company Contributions', color='white', fontsize=16)
    ax.set_xlabel('Company', fontsize=14)
    ax.set_ylabel('Count', fontsize=14)
    ax.grid(True, which='both', axis='y', color='gray', linestyle='-', linewidth=0.5, alpha=0.5)
    ax.set_axisbelow(True)

    for spine in ax.spines.values():
        spine.set_color('white')
        spine.set_linewidth(2)
    ax.spines['right'].set_visible(False)
    ax.spines['top'].set_visible(False)

    #plt.show()
    return fig