Config Dashbprard
This commit is contained in:
207
show_plots.py
207
show_plots.py
@@ -718,128 +718,155 @@ plt.show()
|
||||
|
||||
##
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# %% Dashboard
|
||||
# %% Dashboard
|
||||
import pandas as pd
|
||||
import matplotlib.pyplot as plt
|
||||
import seaborn as sns
|
||||
from datetime import datetime
|
||||
import matplotlib.dates as mdates
|
||||
import numpy as np
|
||||
from matplotlib.gridspec import GridSpec
|
||||
|
||||
def to_numeric_comma(s: pd.Series) -> pd.Series:
|
||||
# accepts 1.5 and 1,5
|
||||
return pd.to_numeric(s.astype(str).str.replace(",", ".", regex=False), errors="coerce")
|
||||
|
||||
# Load the data
|
||||
file_path = '/home/shahin/Lab/Doktorarbeit/Barcelona/Data/Join_edssandsub.tsv'
|
||||
df = pd.read_csv(file_path, sep='\t')
|
||||
|
||||
# Rename columns to remove 'result.' prefix and handle spaces
|
||||
# Rename columns to remove 'result.' prefix and replace spaces
|
||||
column_mapping = {}
|
||||
for col in df.columns:
|
||||
if col.startswith('result.'):
|
||||
new_name = col.replace('result.', '')
|
||||
# Handle spaces in column names (replace with underscores if needed)
|
||||
new_name = new_name.replace(' ', '_')
|
||||
new_name = col.replace('result.', '').replace(' ', '_')
|
||||
column_mapping[col] = new_name
|
||||
df = df.rename(columns=column_mapping)
|
||||
|
||||
# Convert MedDatum to datetime
|
||||
df['MedDatum'] = pd.to_datetime(df['MedDatum'])
|
||||
# Parse MedDatum safely
|
||||
df['MedDatum'] = pd.to_datetime(df['MedDatum'], errors='coerce')
|
||||
|
||||
# Check what columns actually exist in the dataset
|
||||
print("Available columns:")
|
||||
print(df.columns.tolist())
|
||||
print("\nFirst few rows:")
|
||||
print(df.head())
|
||||
# Patient
|
||||
patient_id = '6389d658'
|
||||
patient_data = df[df['unique_id'] == patient_id].sort_values('MedDatum').copy()
|
||||
if patient_data.empty:
|
||||
raise ValueError(f"No data found for patient: {patient_id}")
|
||||
|
||||
# Hardcode specific patient names
|
||||
patient_names = ['2bf8486d']
|
||||
# Functional systems + EDSS
|
||||
edss_col, edss_title = ('GT.EDSS', 'EDSS')
|
||||
|
||||
# Define the functional systems (columns to plot) - adjust based on actual column names
|
||||
functional_systems = ['EDSS', 'Visual', 'Sensory', 'Motor', 'Brainstem', 'Cerebellar', 'Autonomic', 'Bladder', 'Intellectual']
|
||||
functional_systems = [
|
||||
('GT.VISUAL_OPTIC_FUNCTIONS', 'Visual / Optic'),
|
||||
('GT.CEREBELLAR_FUNCTIONS', 'Cerebellar'),
|
||||
('GT.BRAINSTEM_FUNCTIONS', 'Brainstem'),
|
||||
('GT.SENSORY_FUNCTIONS', 'Sensory'),
|
||||
('GT.PYRAMIDAL_FUNCTIONS', 'Pyramidal (Motor)'),
|
||||
('GT.AMBULATION', 'Ambulation'),
|
||||
('GT.CEREBRAL_FUNCTIONS', 'Cerebral'),
|
||||
('GT.BOWEL_AND_BLADDER_FUNCTIONS', 'Bowel & Bladder'),
|
||||
]
|
||||
|
||||
# Create subplots horizontally (2 columns, adjust rows as needed)
|
||||
num_plots = len(functional_systems)
|
||||
num_cols = 2
|
||||
num_rows = (num_plots + num_cols - 1) // num_cols # Ceiling division
|
||||
# y-axis max rules
|
||||
ymax_by_col = {
|
||||
'GT.PYRAMIDAL_FUNCTIONS': 6,
|
||||
'GT.SENSORY_FUNCTIONS': 6,
|
||||
'GT.BOWEL_AND_BLADDER_FUNCTIONS': 6,
|
||||
'GT.VISUAL_OPTIC_FUNCTIONS': 6,
|
||||
'GT.CEREBELLAR_FUNCTIONS': 5,
|
||||
'GT.CEREBRAL_FUNCTIONS': 5,
|
||||
'GT.BRAINSTEM_FUNCTIONS': 5,
|
||||
'GT.EDSS': 10,
|
||||
}
|
||||
default_ymax = 6
|
||||
|
||||
fig, axes = plt.subplots(num_rows, num_cols, figsize=(15, 4*num_rows), sharex=False) # Changed sharex=False
|
||||
if num_plots == 1:
|
||||
axes = [axes]
|
||||
elif num_rows == 1:
|
||||
axes = axes
|
||||
else:
|
||||
axes = axes.flatten()
|
||||
# ---------- Build shared "event dates" ticks ----------
|
||||
cols_for_dates = [edss_col] + [c for c, _ in functional_systems]
|
||||
event_dates = []
|
||||
|
||||
# Plot for the hardcoded patient
|
||||
for i, system in enumerate(functional_systems):
|
||||
# Filter data for this specific patient
|
||||
patient_data = df[df['unique_id'] == patient_names[0]].sort_values('MedDatum')
|
||||
for c in cols_for_dates:
|
||||
if c in patient_data.columns:
|
||||
y = to_numeric_comma(patient_data[c]) # <-- changed
|
||||
x = patient_data['MedDatum']
|
||||
tmp = pd.DataFrame({"x": x, "y": y}).dropna(subset=["x", "y"])
|
||||
event_dates.extend(tmp["x"].tolist())
|
||||
|
||||
# Check if patient data exists
|
||||
if patient_data.empty:
|
||||
print(f"No data found for patient: {patient_names[0]}")
|
||||
continue
|
||||
event_dates = sorted(pd.Series(event_dates).drop_duplicates().tolist())
|
||||
|
||||
# Check if the system column exists in the data
|
||||
if system in patient_data.columns:
|
||||
# Plot the specific functional system
|
||||
if not patient_data[system].isna().all():
|
||||
axes[i].plot(patient_data['MedDatum'], patient_data[system], marker='o', linewidth=2, label=system)
|
||||
axes[i].set_ylabel('Score')
|
||||
axes[i].set_title(f'Functional System: {system}')
|
||||
axes[i].grid(True, alpha=0.3)
|
||||
axes[i].legend()
|
||||
else:
|
||||
axes[i].set_title(f'Functional System: {system} (No data)')
|
||||
axes[i].set_ylabel('Score')
|
||||
axes[i].grid(True, alpha=0.3)
|
||||
max_ticks = 8
|
||||
if len(event_dates) > max_ticks:
|
||||
idx = np.linspace(0, len(event_dates) - 1, max_ticks, dtype=int)
|
||||
event_dates = [event_dates[i] for i in idx]
|
||||
|
||||
# ---------- A4 figure ----------
|
||||
fig = plt.figure(figsize=(11.69, 8.27))
|
||||
gs = GridSpec(nrows=3, ncols=4, figure=fig, height_ratios=[2.0, 1.0, 1.0], hspace=0.5, wspace=0.35)
|
||||
|
||||
def style_time_axis(ax, show_labels=True):
|
||||
ax.set_xticks(event_dates)
|
||||
ax.xaxis.set_major_formatter(mdates.DateFormatter('%Y-%m'))
|
||||
ax.tick_params(axis='x', rotation=30, labelsize=8, pad=2)
|
||||
if not show_labels:
|
||||
ax.tick_params(labelbottom=False)
|
||||
|
||||
# ---------- EDSS main plot ----------
|
||||
ax_main = fig.add_subplot(gs[0, :])
|
||||
|
||||
if edss_col in patient_data.columns:
|
||||
y = to_numeric_comma(patient_data[edss_col]) # <-- changed
|
||||
x = patient_data['MedDatum']
|
||||
plot_df = pd.DataFrame({"x": x, "y": y}).dropna(subset=["x", "y"]).sort_values("x")
|
||||
|
||||
ax_main.set_title(edss_title, fontsize=14, fontweight='bold')
|
||||
ax_main.set_ylabel("Score")
|
||||
ax_main.set_ylim(0, ymax_by_col.get(edss_col, default_ymax))
|
||||
ax_main.grid(True, alpha=0.3)
|
||||
|
||||
if not plot_df.empty:
|
||||
ax_main.plot(plot_df["x"], plot_df["y"], marker='o', linewidth=3, color='tab:red')
|
||||
else:
|
||||
# Try to find column with similar name (case insensitive)
|
||||
found_column = None
|
||||
for col in df.columns:
|
||||
if system.lower() in col.lower():
|
||||
found_column = col
|
||||
break
|
||||
ax_main.set_title("EDSS (no numeric data)", fontsize=14, fontweight='bold')
|
||||
else:
|
||||
ax_main.set_title("EDSS (missing column GT.EDSS)", fontsize=14, fontweight='bold')
|
||||
ax_main.set_ylim(0, ymax_by_col.get(edss_col, 10))
|
||||
ax_main.grid(True, alpha=0.3)
|
||||
|
||||
if found_column:
|
||||
print(f"Found similar column: {found_column}")
|
||||
if not patient_data[found_column].isna().all():
|
||||
axes[i].plot(patient_data['MedDatum'], patient_data[found_column], marker='o', linewidth=2, label=found_column)
|
||||
axes[i].set_ylabel('Score')
|
||||
axes[i].set_title(f'Functional System: {system} (found as: {found_column})')
|
||||
axes[i].grid(True, alpha=0.3)
|
||||
axes[i].legend()
|
||||
style_time_axis(ax_main)
|
||||
|
||||
# ---------- Small aligned plots ----------
|
||||
small_axes = []
|
||||
for k, (col, title) in enumerate(functional_systems):
|
||||
r = 1 + (k // 4)
|
||||
c = (k % 4)
|
||||
ax = fig.add_subplot(gs[r, c], sharex=ax_main)
|
||||
small_axes.append(ax)
|
||||
|
||||
ymax = ymax_by_col.get(col, default_ymax)
|
||||
ax.set_title(title, fontsize=10)
|
||||
ax.set_ylabel("Score")
|
||||
ax.set_ylim(0, ymax)
|
||||
ax.grid(True, alpha=0.3)
|
||||
|
||||
if col in patient_data.columns:
|
||||
y = to_numeric_comma(patient_data[col]) # <-- changed
|
||||
x = patient_data['MedDatum']
|
||||
plot_df = pd.DataFrame({"x": x, "y": y}).dropna(subset=["x", "y"]).sort_values("x")
|
||||
|
||||
if not plot_df.empty:
|
||||
ax.plot(plot_df["x"], plot_df["y"], marker='o', linewidth=2, color='tab:blue')
|
||||
else:
|
||||
axes[i].set_title(f'Functional System: {system} (Column not found)')
|
||||
axes[i].set_ylabel('Score')
|
||||
axes[i].grid(True, alpha=0.3)
|
||||
ax.set_title(f"{title} (no data)", fontsize=10)
|
||||
else:
|
||||
ax.set_title(f"{title} (missing)", fontsize=10)
|
||||
|
||||
# Hide empty subplots
|
||||
for i in range(len(functional_systems), len(axes)):
|
||||
axes[i].set_visible(False)
|
||||
style_time_axis(ax)
|
||||
|
||||
# Set x-axis label for the last row only
|
||||
for i in range(len(functional_systems)):
|
||||
if i >= len(axes) - num_cols: # Last row
|
||||
axes[i].set_xlabel('Date')
|
||||
|
||||
# Force date formatting on all axes
|
||||
for ax in axes:
|
||||
ax.tick_params(axis='x', rotation=45)
|
||||
ax.xaxis.set_major_formatter(plt.matplotlib.dates.DateFormatter('%Y-%m-%d'))
|
||||
ax.xaxis.set_major_locator(plt.matplotlib.dates.MonthLocator())
|
||||
|
||||
# Automatically format x-axis dates
|
||||
plt.gcf().autofmt_xdate()
|
||||
# Hide x tick labels on first row of small plots
|
||||
for ax in small_axes[:4]:
|
||||
ax.tick_params(labelbottom=False)
|
||||
|
||||
plt.tight_layout()
|
||||
fig.subplots_adjust(hspace=0.7)
|
||||
plt.show()
|
||||
|
||||
##
|
||||
|
||||
|
||||
# %% Table
|
||||
import pandas as pd
|
||||
import matplotlib.pyplot as plt
|
||||
|
||||
Reference in New Issue
Block a user