Spaces:
Sleeping
Sleeping
Create charts_advanced.py
Browse files- charts_advanced.py +343 -0
charts_advanced.py
ADDED
@@ -0,0 +1,343 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import pandas as pd
|
2 |
+
import matplotlib.pyplot as plt
|
3 |
+
from collections import Counter
|
4 |
+
import matplotlib.ticker as ticker
|
5 |
+
|
6 |
+
def category_chart(file_path):
|
7 |
+
plt.close('all')
|
8 |
+
# Define expert to specialty mapping
|
9 |
+
expert_specialties = {
|
10 |
+
"mireille": "Security Trust",
|
11 |
+
"khawla": "Network Security",
|
12 |
+
"guillaume": "Distributed Networks",
|
13 |
+
"vincent": "USIM Management",
|
14 |
+
"pierre": "Eco-Design",
|
15 |
+
"ly-thanh": "Trend Analysis",
|
16 |
+
"nicolas": "Satellite Networks",
|
17 |
+
"dorin": "Emergency Communication"
|
18 |
+
}
|
19 |
+
|
20 |
+
# Load the Excel file
|
21 |
+
data = pd.read_excel(file_path)
|
22 |
+
|
23 |
+
# Assuming experts are listed in a column named 'Experts'
|
24 |
+
# This part might need to be adjusted based on the actual structure of your Excel file
|
25 |
+
experts = data['Expert'].dropna()
|
26 |
+
|
27 |
+
# Map experts to their specialties
|
28 |
+
specialties = experts.apply(lambda expert: expert_specialties.get(expert.strip(), "Other"))
|
29 |
+
|
30 |
+
# Count occurrences
|
31 |
+
specialty_counts = specialties.value_counts()
|
32 |
+
|
33 |
+
# Convert to DataFrame for plotting
|
34 |
+
specialty_counts_df = specialty_counts.reset_index()
|
35 |
+
specialty_counts_df.columns = ['Specialty', 'Count']
|
36 |
+
|
37 |
+
# Plotting
|
38 |
+
plt.style.use('dark_background')
|
39 |
+
fig, ax = plt.subplots(figsize=(14, 14))
|
40 |
+
ax.set_facecolor('#222c52')
|
41 |
+
fig.patch.set_facecolor('#222c52')
|
42 |
+
|
43 |
+
# Alternating colors for the bars
|
44 |
+
colors = ['#08F7FE' if i % 2 == 0 else '#FE53BB' for i in range(len(specialty_counts_df))]
|
45 |
+
specialty_counts_df.plot(kind='bar', x='Specialty', y='Count', ax=ax, color=colors, edgecolor=colors, alpha=0.5, linewidth=5, legend=None)
|
46 |
+
|
47 |
+
# Set chart details
|
48 |
+
ax.xaxis.label.set_color('white')
|
49 |
+
ax.yaxis.label.set_color('white')
|
50 |
+
ax.tick_params(axis='x', colors='white', labelsize=12, direction='out', length=6, width=2, rotation=42)
|
51 |
+
ax.tick_params(axis='y', colors='white', labelsize=12, direction='out', length=6, width=2)
|
52 |
+
ax.set_title('Most Used Expert Specialties', color='white', fontsize=16)
|
53 |
+
ax.set_xlabel('Specialty', fontsize=14)
|
54 |
+
ax.set_ylabel('Count', fontsize=14)
|
55 |
+
ax.grid(True, which='both', axis='y', color='gray', linestyle='-', linewidth=0.5, alpha=0.5)
|
56 |
+
ax.set_axisbelow(True)
|
57 |
+
|
58 |
+
for spine in ax.spines.values():
|
59 |
+
spine.set_color('white')
|
60 |
+
spine.set_linewidth(2)
|
61 |
+
ax.spines['right'].set_visible(False)
|
62 |
+
ax.spines['top'].set_visible(False)
|
63 |
+
|
64 |
+
return fig
|
65 |
+
|
66 |
+
|
67 |
+
|
68 |
+
|
69 |
+
def status_chart(file_path):
|
70 |
+
# Load the Excel file
|
71 |
+
plt.close('all')
|
72 |
+
data = pd.read_excel(file_path)
|
73 |
+
|
74 |
+
# Calculate the frequency of each status
|
75 |
+
status_counts = data['Status'].value_counts()
|
76 |
+
|
77 |
+
# Define colors with 50% opacity
|
78 |
+
colors = ['#08F7FE80', '#FE53BB80',
|
79 |
+
'#fff236de', '#90ff00bf'] # '80' for 50% opacity
|
80 |
+
|
81 |
+
# Plotting
|
82 |
+
fig, ax = plt.subplots()
|
83 |
+
fig.patch.set_facecolor('#222c52') # Set the background color of the figure
|
84 |
+
ax.set_facecolor('#222c52') # Set the background color of the axes
|
85 |
+
wedges, texts, autotexts = ax.pie(status_counts, autopct='%1.1f%%', startangle=90, colors=colors,
|
86 |
+
wedgeprops=dict(edgecolor='white', linewidth=1.5))
|
87 |
+
|
88 |
+
# Set legend
|
89 |
+
ax.legend(wedges, status_counts.index, title="Document Status", loc="center left", bbox_to_anchor=(1, 0, 0.5, 1))
|
90 |
+
|
91 |
+
ax.set_ylabel('') # Remove the y-label
|
92 |
+
ax.set_title('Document Status Distribution', color='white')
|
93 |
+
|
94 |
+
plt.setp(autotexts, size=8, weight="bold", color="white")
|
95 |
+
|
96 |
+
return fig
|
97 |
+
|
98 |
+
|
99 |
+
|
100 |
+
def plot_glowing_line_with_dots_enhanced(ax, x, y, color, label, glow_size=10, base_linewidth=3, markersize=8):
|
101 |
+
for i in range(1, glow_size + 1):
|
102 |
+
alpha_value = (1.0 / glow_size) * (i / (glow_size / 2))
|
103 |
+
if alpha_value > 1.0:
|
104 |
+
alpha_value = 1.0
|
105 |
+
linewidth = base_linewidth * i * 0.5
|
106 |
+
ax.plot(x, y, color=color, linewidth=linewidth, alpha=alpha_value * 0.1)
|
107 |
+
ax.plot(x, y, color=color, linewidth=base_linewidth, marker='o', linestyle='-', label=label, markersize=markersize)
|
108 |
+
|
109 |
+
def company_document_type(file_path, company_names):
|
110 |
+
plt.close('all')
|
111 |
+
# Convert company_names to a list if it's a string
|
112 |
+
if isinstance(company_names, str):
|
113 |
+
company_names = [name.strip() for name in company_names.split(',')] # Ensure it's a list even for single company name
|
114 |
+
|
115 |
+
df = pd.read_excel(file_path)
|
116 |
+
plt.style.use('dark_background')
|
117 |
+
fig, ax = plt.subplots(figsize=(14, 8))
|
118 |
+
ax.set_facecolor('#222c52')
|
119 |
+
fig.patch.set_facecolor('#222c52')
|
120 |
+
|
121 |
+
colors = ['#08F7FE', '#FE53BB', '#fff236'] # Assign more colors for more companies
|
122 |
+
|
123 |
+
max_count = 0
|
124 |
+
for index, company_name in enumerate(company_names):
|
125 |
+
df_company = df[df['Source'].str.contains(company_name, case=False, na=False)]
|
126 |
+
document_counts = df_company['Type'].value_counts()
|
127 |
+
all_document_types = df['Type'].unique()
|
128 |
+
document_counts = document_counts.reindex(all_document_types, fill_value=0)
|
129 |
+
|
130 |
+
x_data = document_counts.index
|
131 |
+
y_data = document_counts.values
|
132 |
+
ax.fill_between(x_data, y_data, -0.2, color=colors[index % len(colors)], alpha=0.1)
|
133 |
+
plot_glowing_line_with_dots_enhanced(ax, x_data, y_data, colors[index % len(colors)], company_name, base_linewidth=4)
|
134 |
+
|
135 |
+
if max_count < max(y_data):
|
136 |
+
max_count = max(y_data)
|
137 |
+
|
138 |
+
ax.set_xticks(range(len(all_document_types)))
|
139 |
+
ax.set_xticklabels(all_document_types, rotation=45, fontsize=12, fontweight='bold')
|
140 |
+
ax.yaxis.set_major_locator(ticker.MaxNLocator(integer=True))
|
141 |
+
ax.set_ylabel('Count', color='white')
|
142 |
+
ax.set_title('Document Types Contributed by Companies')
|
143 |
+
ax.grid(True, which='both', axis='both', color='gray', linestyle='-', linewidth=0.5, alpha=0.5)
|
144 |
+
ax.set_axisbelow(True)
|
145 |
+
|
146 |
+
plt.ylim(-0.2, max_count + 1)
|
147 |
+
|
148 |
+
for spine in ax.spines.values():
|
149 |
+
spine.set_color('white')
|
150 |
+
spine.set_linewidth(2)
|
151 |
+
|
152 |
+
ax.spines['right'].set_visible(False)
|
153 |
+
ax.spines['top'].set_visible(False)
|
154 |
+
ax.spines['left'].set_position(('data', 0))
|
155 |
+
plt.legend(facecolor='#222c52', edgecolor='white', fontsize=12)
|
156 |
+
|
157 |
+
return fig
|
158 |
+
|
159 |
+
|
160 |
+
|
161 |
+
def chart_by_expert(file_path, expert_name):
|
162 |
+
plt.close('all')
|
163 |
+
# Load the Excel file
|
164 |
+
data = pd.read_excel(file_path)
|
165 |
+
|
166 |
+
parts = expert_name.split('/')
|
167 |
+
|
168 |
+
# The name would be the second part, trim spaces
|
169 |
+
name = parts[1].strip()
|
170 |
+
# Filter data for the specified expert
|
171 |
+
filtered_data = data[data['Expert'] == name.lower()]
|
172 |
+
|
173 |
+
# Define merge entities mapping
|
174 |
+
merge_entities = {
|
175 |
+
"Nokia Shanghai Bell": "Nokia",
|
176 |
+
"Qualcomm Korea": "Qualcomm",
|
177 |
+
"Qualcomm Incorporated": "Qualcomm",
|
178 |
+
"Huawei Technologies R&D UK": "Huawei",
|
179 |
+
"Hughes Network Systems": "Hughes",
|
180 |
+
"HUGHES Network Systems": "Hughes",
|
181 |
+
"Hughes Network systems": "Hughes",
|
182 |
+
"HUGHES Network Systems Ltd": "Hughes",
|
183 |
+
"KT Corp.": "KT Corporation",
|
184 |
+
"LG Electronics Inc.": "LG Electronics",
|
185 |
+
"LG Uplus": "LG Electronics",
|
186 |
+
"OPPO (chongqing) Intelligence": "OPPO",
|
187 |
+
"Samsung Electronics GmbH": "Samsung",
|
188 |
+
"China Mobile International Ltd": "China Mobile",
|
189 |
+
"NOVAMINT": "Novamint",
|
190 |
+
"Eutelsat": "Eutelsat Group",
|
191 |
+
"Inmarsat Viasat": "Inmarsat",
|
192 |
+
"China Telecommunications": "China Telecom",
|
193 |
+
"SES S.A.": "SES",
|
194 |
+
"Ericsson GmbH": "Ericsson",
|
195 |
+
"JSAT": "SKY Perfect JSAT",
|
196 |
+
"NEC Europe Ltd": "NEC",
|
197 |
+
"Fraunhofer IIS": "Fraunhofer",
|
198 |
+
"Hugues Network Systems": "Hughes"
|
199 |
+
}
|
200 |
+
|
201 |
+
# Normalize company names within each cell
|
202 |
+
def normalize_companies(company_list, merge_entities):
|
203 |
+
normalized = set() # Use a set to avoid duplicates within the same cell
|
204 |
+
for company in company_list:
|
205 |
+
normalized_name = merge_entities.get(company.strip(), company.strip())
|
206 |
+
normalized.add(normalized_name)
|
207 |
+
return list(normalized)
|
208 |
+
|
209 |
+
# Prepare the filtered data
|
210 |
+
sources = filtered_data['Source'].dropna()
|
211 |
+
split_sources = sources.apply(lambda x: normalize_companies(x.split(', '), merge_entities))
|
212 |
+
|
213 |
+
# Flatten the list of lists while applying the merge rules
|
214 |
+
all_sources = [company for sublist in split_sources for company in sublist]
|
215 |
+
|
216 |
+
# Count occurrences
|
217 |
+
source_counts = Counter(all_sources)
|
218 |
+
top_10_sources = source_counts.most_common(10)
|
219 |
+
|
220 |
+
# Convert to DataFrame for plotting
|
221 |
+
top_10_df = pd.DataFrame(top_10_sources, columns=['Company', 'Count'])
|
222 |
+
|
223 |
+
# Plotting
|
224 |
+
plt.style.use('dark_background')
|
225 |
+
fig, ax = plt.subplots(figsize=(14, 11))
|
226 |
+
ax.set_facecolor('#222c52')
|
227 |
+
fig.patch.set_facecolor('#222c52')
|
228 |
+
|
229 |
+
# Alternating colors for the bars
|
230 |
+
colors = ['#08F7FE' if i % 2 == 0 else '#FE53BB' for i in range(len(top_10_df))]
|
231 |
+
top_10_df.plot(kind='bar', x='Company', y='Count', ax=ax, color=colors, edgecolor=colors, alpha=0.5, linewidth=5)
|
232 |
+
|
233 |
+
# Set chart details
|
234 |
+
ax.xaxis.label.set_color('white')
|
235 |
+
ax.yaxis.label.set_color('white')
|
236 |
+
ax.tick_params(axis='x', colors='white', labelsize=12, direction='out', length=6, width=2, rotation=45)
|
237 |
+
ax.tick_params(axis='y', colors='white', labelsize=12, direction='out', length=6, width=2)
|
238 |
+
ax.set_title(f"Top 10 Cotributors for Expert '{expert_name}'", color='white', fontsize=16)
|
239 |
+
ax.set_xlabel('Company', fontsize=14)
|
240 |
+
ax.set_ylabel('Count', fontsize=14)
|
241 |
+
ax.yaxis.set_major_locator(ticker.MaxNLocator(integer=True))
|
242 |
+
ax.grid(True, which='both', axis='y', color='gray', linestyle='-', linewidth=0.5, alpha=0.5)
|
243 |
+
ax.set_axisbelow(True)
|
244 |
+
|
245 |
+
for spine in ax.spines.values():
|
246 |
+
spine.set_color('white')
|
247 |
+
spine.set_linewidth(2)
|
248 |
+
ax.spines['right'].set_visible(False)
|
249 |
+
ax.spines['top'].set_visible(False)
|
250 |
+
|
251 |
+
return fig
|
252 |
+
|
253 |
+
|
254 |
+
|
255 |
+
# @title Top 10 des entreprises en termes de publications
|
256 |
+
|
257 |
+
|
258 |
+
|
259 |
+
def generate_company_chart(file_path):
|
260 |
+
# plt.close('all')
|
261 |
+
# Define merge entities mapping
|
262 |
+
merge_entities = {
|
263 |
+
"Nokia Shanghai Bell": "Nokia",
|
264 |
+
"Qualcomm Korea": "Qualcomm",
|
265 |
+
"Qualcomm Incorporated": "Qualcomm",
|
266 |
+
"Huawei Technologies R&D UK": "Huawei",
|
267 |
+
"Hughes Network Systems": "Hughes",
|
268 |
+
"HUGHES Network Systems": "Hughes",
|
269 |
+
"Hughes Network systems": "Hughes",
|
270 |
+
"HUGHES Network Systems Ltd": "Hughes",
|
271 |
+
"KT Corp.": "KT Corporation",
|
272 |
+
"Deutsche Telekom AG": "Deutsche Telekom",
|
273 |
+
"LG Electronics Inc.": "LG Electronics",
|
274 |
+
"LG Uplus": "LG Electronics",
|
275 |
+
"OPPO (chongqing) Intelligence": "OPPO",
|
276 |
+
"Samsung Electronics GmbH": "Samsung",
|
277 |
+
"China Mobile International Ltd": "China Mobile",
|
278 |
+
"NOVAMINT": "Novamint",
|
279 |
+
"Eutelsat": "Eutelsat Group",
|
280 |
+
"Inmarsat Viasat": "Inmarsat",
|
281 |
+
"China Telecommunications": "China Telecom",
|
282 |
+
"SES S.A.": "SES",
|
283 |
+
"Ericsson GmbH": "Ericsson",
|
284 |
+
"JSAT": "SKY Perfect JSAT",
|
285 |
+
"NEC Europe Ltd": "NEC",
|
286 |
+
"Fraunhofer IIS": "Fraunhofer",
|
287 |
+
"Hugues Network Systems": "Hughes"
|
288 |
+
}
|
289 |
+
|
290 |
+
# Function to normalize company names within each cell
|
291 |
+
def normalize_companies(company_list, merge_entities):
|
292 |
+
normalized = set() # Use a set to avoid duplicates within the same cell
|
293 |
+
for company in company_list:
|
294 |
+
normalized_name = merge_entities.get(company.strip(), company.strip())
|
295 |
+
normalized.add(normalized_name)
|
296 |
+
return list(normalized)
|
297 |
+
|
298 |
+
# Load the Excel file
|
299 |
+
data = pd.read_excel(file_path)
|
300 |
+
|
301 |
+
# Prepare the data
|
302 |
+
sources = data['Source'].dropna()
|
303 |
+
split_sources = sources.apply(lambda x: normalize_companies(x.split(', '), merge_entities))
|
304 |
+
|
305 |
+
# Flatten the list of lists while applying the merge rules
|
306 |
+
all_sources = [company for sublist in split_sources for company in sublist]
|
307 |
+
|
308 |
+
# Count occurrences
|
309 |
+
source_counts = Counter(all_sources)
|
310 |
+
top_10_sources = source_counts.most_common(10)
|
311 |
+
|
312 |
+
# Convert to DataFrame for plotting
|
313 |
+
top_10_df = pd.DataFrame(top_10_sources, columns=['Company', 'Count'])
|
314 |
+
|
315 |
+
# Plotting
|
316 |
+
plt.style.use('dark_background')
|
317 |
+
fig, ax = plt.subplots(figsize=(14, 12))
|
318 |
+
ax.set_facecolor('#222c52')
|
319 |
+
fig.patch.set_facecolor('#222c52')
|
320 |
+
|
321 |
+
# Alternating colors for the bars
|
322 |
+
colors = ['#08F7FE' if i % 2 == 0 else '#FE53BB' for i in range(len(top_10_df))]
|
323 |
+
top_10_df.plot(kind='bar', x='Company', y='Count', ax=ax, color=colors, edgecolor=colors, alpha=0.5, linewidth=5, legend=None)
|
324 |
+
|
325 |
+
# Set chart details
|
326 |
+
ax.xaxis.label.set_color('white')
|
327 |
+
ax.yaxis.label.set_color('white')
|
328 |
+
ax.tick_params(axis='x', colors='white', labelsize=16, direction='out', length=6, width=2, rotation=37)
|
329 |
+
ax.tick_params(axis='y', colors='white', labelsize=12, direction='out', length=6, width=2)
|
330 |
+
ax.set_title('Top 10 Contributors: Ranking Company Contributions', color='white', fontsize=16)
|
331 |
+
ax.set_xlabel('Company', fontsize=14)
|
332 |
+
ax.set_ylabel('Count', fontsize=14)
|
333 |
+
ax.grid(True, which='both', axis='y', color='gray', linestyle='-', linewidth=0.5, alpha=0.5)
|
334 |
+
ax.set_axisbelow(True)
|
335 |
+
|
336 |
+
for spine in ax.spines.values():
|
337 |
+
spine.set_color('white')
|
338 |
+
spine.set_linewidth(2)
|
339 |
+
ax.spines['right'].set_visible(False)
|
340 |
+
ax.spines['top'].set_visible(False)
|
341 |
+
|
342 |
+
#plt.show()
|
343 |
+
return fig
|