smiuser/hpos-data
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix errors in auto dye analysis

Browse Source
This commit is contained in:
Pritimay Sarkar
2023-12-07 22:09:18 +05:30
parent f96b1cf026
commit 2f14aa6ca6
2 changed files with 286 additions and 251 deletions
Download Patch File Download Diff File Expand all files Collapse all files

76
cloud-functions/python/functions/performance/main.py
View File

@@ -83,6 +83,7 @@ def performance(request):
curdir = os.getcwd()
path_delim = '/'
output_filename = ''
precision_threshold = 0.009
accuracy_threshold = 0.02
@@ -139,36 +140,24 @@ def performance(request):
df_reference_device.index.name = 'Solution'
df_reference_device.columns.name = 'Wavelength'
texts_to_check = ['T', 'K']
df['solution'] = df['name'].str.extract(f"({'|'.join(texts_to_check)})", flags=re.IGNORECASE)
df['solution'] = df['solution'].replace({'T': 'Tartrazine', 'K': 'KMnO4'}, regex=True)
if not df.empty:
conditions = [df['name'].str.contains('Tar', case=False, na=False),
df['name'].str.contains('KM', case=False, na=False)]
choices = ['Tartrazine', 'KMnO4']
df['solution'] = np.select(conditions, choices, default=None)
def extract_numbers(s):
match = re.match(r'\d+', s)
match = re.search(r'-(\d+)', s) or re.search(r'(\d+)', s)
if match:
return int(match.group())
return int(match.group(1))
else:
return None
df["concentration"] = df['name'].apply(extract_numbers)
df['absorbance'] = df.apply(lambda row: row['led1Average'] if row['solution'] == 'Tartrazine' else row['led3Average'], axis=1)
fig, ax = plt.subplots()
unique_solutions = df['solution'].unique()
for solution in unique_solutions:
solution_data = df[df['solution'] == solution]
concentration_means = solution_data.groupby('concentration')['absorbance'].mean()
ax.plot(concentration_means.index, concentration_means.values, marker='o', linestyle='-', label=f'Mean Absorbance for {solution}')
ax.set_title('Mean Absorbance for Each Solution')
ax.set_xlabel('Concentration')
ax.set_ylabel('Mean Absorbance')
ax.legend()
df_precision_acc = df[["deviceId", "solution", "concentration", "led1Average", "led3Average", "absorbance"]].groupby(["deviceId", "solution", "concentration"]).describe()["absorbance"][["count", "min", "max", "mean"]]
df_precision_acc['precision'] = df_precision_acc['max'] - df_precision_acc['min']
@@ -249,9 +238,50 @@ def performance(request):
'value': 'Pass',
'format': green_format})
wks1 = workbook.add_worksheet('abs_plot')
wks1.write(0,0,'Abs Plot')
# Write the header
wks1.write(0, 0, 'Solution')
wks1.write(0, 1, 'Slope')
wks1.write(0, 2, 'Intercept')
row = 1
fig, ax = plt.subplots()
filtered_df = df[df['solution'].isin(['KMnO4', 'Tartrazine'])]
for solution in filtered_df['solution'].unique():
if pd.notna(solution):
solution_data = df[df['solution'] == solution]
concentration_means = solution_data.groupby('concentration')['absorbance'].mean()
coefficients = np.polyfit(concentration_means.index, concentration_means.values, 1)
print(f'Coefficients for {solution}: Slope={coefficients[0]}, Intercept={coefficients[1]}')
ax.plot(concentration_means.index, concentration_means.values, marker='o', linestyle='-', label=f'Mean Absorbance for {solution}')
ax.plot(concentration_means.index, np.polyval(coefficients, concentration_means.index), linestyle='--', label=f'Linear Fit for {solution}')
annotation_text = f'Slope: {coefficients[0]:.4f}\nIntercept: {coefficients[1]:.4f}'
ax.text(concentration_means.index[-1] + 5, np.polyval(coefficients, concentration_means.index[-1]), annotation_text, fontsize=10, verticalalignment='center')
wks1.write(row, 0, solution)
wks1.write(row, 1, coefficients[0])
wks1.write(row, 2, coefficients[1])
row += 1
# writer.save()
ax.set_title('Mean Absorbance for Each Solution')
ax.set_xlabel('Concentration')
ax.set_ylabel('Mean Absorbance')
ax.legend()
imgdata=io.BytesIO()
fig.savefig(imgdata, format='png')
wks1.insert_image(2,2, '', {'image_data': imgdata})
@@ -268,6 +298,10 @@ def performance(request):
# df_merged.to_excel(writer, sheet_name="merged_results")
writer.close()
else:
# If df is empty, create an empty Excel file
output_filename = f'/tmp/empty_excel_{datetime.today().strftime("%d_%m_%Y_%H_%M")}.xlsx'
pd.DataFrame().to_excel(output_filename, engine='xlsxwriter', index=False)
# firebase_admin.delete_app(firebase_admin.get_app())

31
scripts/device_accuracy.py
View File

@@ -68,14 +68,18 @@ df_reference_device.columns.name = 'Wavelength'
df = pd.read_excel(curdir + path_delim + "data" + path_delim + "data_06_12_2023_12_47.xlsx", sheet_name="data")
texts_to_check = ['T', 'K']
df['solution'] = df['name'].str.extract(f"({'|'.join(texts_to_check)})", flags=re.IGNORECASE)
df['solution'] = df['solution'].replace({'T': 'Tartrazine', 'K': 'KMnO4'}, regex=True)
if not df.empty:
conditions = [df['name'].str.contains('Tar', case=False, na=False),
df['name'].str.contains('KM', case=False, na=False)]
choices = ['Tartrazine', 'KMnO4']
df['solution'] = np.select(conditions, choices, default=None)
def extract_numbers(s):
match = re.match(r'\d+', s)
match = re.search(r'-(\d+)', s) or re.search(r'(\d+)', s)
if match:
return int(match.group())
return int(match.group(1))
else:
return None
@@ -114,7 +118,6 @@ for idx, row in df_precision_acc.iterrows():
solution = row.name[1]
concentration = str(int(row.name[2]))
# print(concentration)
reference_value = denovix_reference_values[solution][concentration]
try:
reference_value = denovix_reference_values[solution][concentration]
@@ -175,9 +178,9 @@ row = 1
fig, ax = plt.subplots()
unique_solutions = df['solution'].unique()
filtered_df = df[df['solution'].isin(['KMnO4', 'Tartrazine'])]
for solution in unique_solutions:
for solution in filtered_df['solution'].unique():
if pd.notna(solution):
solution_data = df[df['solution'] == solution]
@@ -186,28 +189,21 @@ for solution in unique_solutions:
# Fit a linear regression model
coefficients = np.polyfit(concentration_means.index, concentration_means.values, 1)
# Print the coefficients
print(f'Coefficients for {solution}: Slope={coefficients[0]}, Intercept={coefficients[1]}')
# Plot the mean absorbance
ax.plot(concentration_means.index, concentration_means.values, marker='o', linestyle='-', label=f'Mean Absorbance for {solution}')
# Plot the linear fit
ax.plot(concentration_means.index, np.polyval(coefficients, concentration_means.index), linestyle='--', label=f'Linear Fit for {solution}')
# Add coefficients next to the linear fit trendline
annotation_text = f'Slope: {coefficients[0]:.4f}\nIntercept: {coefficients[1]:.4f}'
ax.text(concentration_means.index[-1] + 5, np.polyval(coefficients, concentration_means.index[-1]), annotation_text, fontsize=10, verticalalignment='center')
# Write the coefficients to the worksheet
wks1.write(row, 0, solution)
wks1.write(row, 1, coefficients[0])
wks1.write(row, 2, coefficients[1])
row += 1
# writer.save()
ax.set_title('Mean Absorbance for Each Solution')
ax.set_xlabel('Concentration')
ax.set_ylabel('Mean Absorbance')
@@ -229,3 +225,8 @@ wks1.insert_image(2,2, '', {'image_data': imgdata})
# df_merged.to_excel(writer, sheet_name="merged_results")
writer.close()
else:
# If df is empty, create an empty Excel file
empty_output_filename = f'data/empty_excel_{datetime.today().strftime("%d_%m_%Y_%H_%M")}.xlsx'
pd.DataFrame().to_excel(empty_output_filename, engine='xlsxwriter', index=False)