pc-123 0.1.0__py3-none-any.whl

pc123/cli.py

@@ -0,0 +1,23 @@
+import sys
+from importlib import resources
+
+def main():
+    if len(sys.argv) < 2:
+        print("Usage: pc-123 <experiment_number>")
+        return
+
+    num = sys.argv[1]
+    try:
+        code = resources.files("pc123.experiments").joinpath(f"exp{num}.py").read_text(encoding="utf-8")
+    except FileNotFoundError:
+        print(f"Experiment {num} not found.")
+        return
+
+    print("=" * 60)
+    print(f"# EXP{num}")
+    print("=" * 60)
+    print()
+    print(code)
+
+if __name__ == "__main__":
+    main()

pc123/experiments/exp1.py

@@ -0,0 +1,21 @@
+# Step 1: Import libraries
+import pandas as pd
+import numpy as np
+
+# Step 2: Load dataset
+df = pd.read_csv('clinical_data.csv')
+
+# Step 3: Display basic information
+print("Dataset Shape:", df.shape)
+print("\nFirst 5 Records:\n", df.head())
+print("\nColumn Names:\n", df.columns.tolist())
+print("\nData Types:\n", df.dtypes)
+
+# Step 4: Generate summary statistics
+print("\nDescriptive Statistics:\n", df.describe())
+
+# Step 5: Check missing values
+print("\nMissing Values:\n", df.isnull().sum())
+
+print("\nDataset Information:")
+df.info()

pc123/experiments/exp2.py

@@ -0,0 +1,25 @@
+# Step 1: Import libraries
+import pandas as pd
+import numpy as np
+
+# Step 2: Load dataset
+df = pd.read_csv('clinical_data.csv')
+
+# Step 3: Check missing values
+print("Missing Values:\n", df.isnull().sum())
+
+# Step 4: Handle missing values
+df_clean = df.dropna()
+df_clean = df.fillna(df.mean(numeric_only=True))
+
+# Step 5: Check and remove duplicate rows
+print("Duplicate Rows:", df_clean.duplicated().sum())
+df_clean.drop_duplicates(inplace=True)
+
+# Step 6: Standardize inconsistent text entries
+df_clean['gender'] = df_clean['gender'].str.strip().str.lower()
+
+# Step 7: Verify cleaned dataset
+print("\nMissing Values After Cleaning:\n", df_clean.isnull().sum())
+print("Duplicate Rows After Cleaning:", df_clean.duplicated().sum())
+df_clean.info()

pc123/experiments/exp3.py

@@ -0,0 +1,39 @@
+# Step 1: Import libraries
+import pandas as pd
+import numpy as np
+
+# Step 2: Load datasets
+demo = pd.read_csv('demographics.csv')
+vitals = pd.read_csv('vitals.csv')
+print(demo.shape, vitals.shape)
+
+# Step 3: Check the key variable for duplicates
+print("Duplicate IDs (demo):", demo['patient_id'].duplicated().sum())
+print("Duplicate IDs (vitals):", vitals['patient_id'].duplicated().sum())
+
+# Step 4: Merge datasets on patient_id
+merged = pd.merge(demo, vitals, on='patient_id', how='inner')  # how='left' keeps all patients from demo
+print("Merged shape:", merged.shape)
+
+# Step 5: Create derived variables
+merged['bmi'] = (merged['weight_kg'] / (merged['height_cm'] / 100) ** 2).round(1)
+
+merged['age_group'] = pd.cut(merged['age'],
+                             bins=[0, 17, 39, 59, 120],
+                             labels=['<18', '18-39', '40-59', '60+'])
+
+merged['bmi_category'] = np.select(
+    [merged['bmi'] < 18.5, merged['bmi'] < 25, merged['bmi'] < 30],
+    ['Underweight', 'Normal', 'Overweight'],
+    default='Obese')
+
+merged['hypertension_flag'] = np.where(merged['sbp_baseline'] >= 140, 1, 0)
+merged['sbp_change'] = merged['sbp_final'] - merged['sbp_baseline']
+
+# Step 6: Verify the transformed dataset
+print(merged[['patient_id', 'bmi', 'age_group', 'bmi_category',
+              'hypertension_flag', 'sbp_change']].head())
+merged.info()
+
+# Step 7: Save the transformed dataset
+merged.to_csv('clinical_transformed.csv', index=False)

pc123/experiments/exp4.py

@@ -0,0 +1,47 @@
+# Step 1: Import libraries
+import pandas as pd
+import matplotlib.pyplot as plt
+
+# Step 2: Load the transformed dataset
+df = pd.read_csv('clinical_transformed.csv')
+
+# Step 3: Bar chart - number of patients in each BMI category
+counts = df['bmi_category'].value_counts()
+plt.figure(figsize=(6, 4))
+plt.bar(counts.index, counts.values, color='steelblue')
+plt.title('Patients by BMI Category')
+plt.xlabel('BMI Category')
+plt.ylabel('Number of Patients')
+plt.tight_layout()
+plt.savefig('bar_bmi_category.png')
+plt.show()
+
+# Step 4: Histogram - distribution of age
+plt.figure(figsize=(6, 4))
+plt.hist(df['age'], bins=10, color='skyblue', edgecolor='black')
+plt.title('Age Distribution of Patients')
+plt.xlabel('Age (years)')
+plt.ylabel('Frequency')
+plt.tight_layout()
+plt.savefig('hist_age.png')
+plt.show()
+
+# Step 5: Box plot - baseline systolic BP by gender
+df.boxplot(column='sbp_baseline', by='gender', figsize=(6, 4))
+plt.title('Baseline Systolic BP by Gender')
+plt.suptitle('')
+plt.xlabel('Gender')
+plt.ylabel('Systolic BP (mmHg)')
+plt.tight_layout()
+plt.savefig('box_sbp_gender.png')
+plt.show()
+
+# Step 6: Compare patient groups - mean change in systolic BP by gender
+print(df.groupby('gender')['sbp_change'].describe())
+
+df.groupby('gender')['sbp_change'].mean().plot(kind='bar', color='steelblue')
+plt.title('Mean Change in Systolic BP by Gender')
+plt.xlabel('Gender')
+plt.ylabel('Mean Change (mmHg)')
+plt.tight_layout()
+plt.show()

pc123/experiments/exp5.py

@@ -0,0 +1,54 @@
+import pandas as pd
+
+# Step 1: Load raw datasets
+raw_demo = pd.read_csv('demographics.csv')
+raw_vitals = pd.read_csv('vitals.csv')   # columns: patient_id, visit, sbp
+
+STUDY = 'STUDY01'
+
+# Step 2: Create DM (Demographics) domain - one row per subject
+dm = pd.DataFrame({
+    'STUDYID': STUDY,
+    'DOMAIN': 'DM',
+    'USUBJID': STUDY + '-' + raw_demo['patient_id'].astype(str),
+    'SUBJID': raw_demo['patient_id'].astype(str),
+    'AGE': raw_demo['age'],
+    'AGEU': 'YEARS',
+    'SEX': raw_demo['gender'].str.strip().str.upper().str[0]
+})
+
+# Step 3: Create VS (Vital Signs) domain - one record per test per visit
+vs = pd.DataFrame({
+    'STUDYID': STUDY,
+    'DOMAIN': 'VS',
+    'USUBJID': STUDY + '-' + raw_vitals['patient_id'].astype(str),
+    'VSTESTCD': 'SYSBP',
+    'VSTEST': 'Systolic Blood Pressure',
+    'VSSTRESN': raw_vitals['sbp'],
+    'VSSTRESU': 'mmHg',
+    'VISIT': raw_vitals['visit'].str.strip().str.upper()
+})
+
+# Visit order: add every visit name that appears in your data
+visit_order = {'SCREENING': 0, 'BASELINE': 1, 'WEEK 4': 2, 'WEEK 8': 3, 'WEEK 12': 4}
+vs['VISITNUM'] = vs['VISIT'].map(visit_order)
+vs['VSBLFL'] = vs['VISIT'].eq('BASELINE').map({True: 'Y', False: ''})
+
+vs = vs.sort_values(['USUBJID', 'VISITNUM']).reset_index(drop=True)
+vs['VSSEQ'] = vs.groupby('USUBJID').cumcount() + 1
+
+# Step 4: Variable labels
+dm.attrs['labels'] = {
+    'STUDYID': 'Study Identifier', 'DOMAIN': 'Domain Abbreviation',
+    'USUBJID': 'Unique Subject Identifier', 'SUBJID': 'Subject Identifier for the Study',
+    'AGE': 'Age', 'AGEU': 'Age Units', 'SEX': 'Sex'}
+vs.attrs['labels'] = {
+    'STUDYID': 'Study Identifier', 'DOMAIN': 'Domain Abbreviation',
+    'USUBJID': 'Unique Subject Identifier', 'VSSEQ': 'Sequence Number',
+    'VSTESTCD': 'Vital Signs Test Short Name', 'VSTEST': 'Vital Signs Test Name',
+    'VSSTRESN': 'Numeric Result/Finding in Standard Units', 'VSSTRESU': 'Standard Units',
+    'VSBLFL': 'Baseline Flag', 'VISITNUM': 'Visit Number', 'VISIT': 'Visit Name'}
+
+# Step 5: Save
+dm.to_csv('dm.csv', index=False)
+vs.to_csv('vs.csv', index=False)

pc123/experiments/exp6.py

@@ -0,0 +1,45 @@
+# Step 1: Import libraries
+import pandas as pd
+import numpy as np
+
+# Step 2: Load SDTM datasets (from Experiment 5)
+dm = pd.read_csv('dm.csv')
+vs = pd.read_csv('vs.csv')
+
+# Step 3: Create ADSL (Subject-Level Analysis Dataset)
+adsl = dm.drop(columns='DOMAIN')
+adsl['AGEGR1'] = pd.cut(adsl['AGE'],
+                        bins=[0, 39, 59, 200],
+                        labels=['<40', '40-59', '>=60']).astype(str)
+adsl['SAFFL'] = 'Y'
+
+# Step 4: Create ADVS (Vital Signs Analysis Dataset)
+advs = vs.merge(adsl[['USUBJID', 'AGE', 'SEX', 'AGEGR1', 'SAFFL']],
+                on='USUBJID', how='left')
+advs['PARAMCD'] = advs['VSTESTCD']
+advs['PARAM'] = advs['VSTEST'] + ' (' + advs['VSSTRESU'] + ')'
+advs['AVAL'] = advs['VSSTRESN']
+advs['AVISIT'] = advs['VISIT']
+advs['AVISITN'] = advs['VISIT'].map({'BASELINE': 0, 'WEEK 12': 12})
+advs['ABLFL'] = np.where(advs['VISIT'] == 'BASELINE', 'Y', '')
+
+# Step 5: Derive baseline, change from baseline and percent change
+base = advs.loc[advs['ABLFL'] == 'Y', ['USUBJID', 'PARAMCD', 'AVAL']]
+base = base.rename(columns={'AVAL': 'BASE'})
+advs = advs.merge(base, on=['USUBJID', 'PARAMCD'], how='left')
+advs['CHG'] = advs['AVAL'] - advs['BASE']
+advs['PCHG'] = (advs['CHG'] / advs['BASE'] * 100).round(1)
+advs.loc[advs['ABLFL'] == 'Y', ['CHG', 'PCHG']] = np.nan  # post-baseline only
+
+# Step 6: Select variables and verify
+advs = advs[['STUDYID', 'USUBJID', 'AGE', 'SEX', 'AGEGR1', 'SAFFL',
+             'PARAMCD', 'PARAM', 'AVISIT', 'AVISITN',
+             'AVAL', 'ABLFL', 'BASE', 'CHG', 'PCHG']]
+advs = advs.sort_values(['USUBJID', 'AVISITN']).reset_index(drop=True)
+print(adsl.head())
+print(advs.head())
+advs.info()
+
+# Step 7: Save the ADaM datasets
+adsl.to_csv('adsl.csv', index=False)
+advs.to_csv('advs.csv', index=False)

pc123/experiments/exp7.py

@@ -0,0 +1,34 @@
+# Step 1: Import libraries
+import pandas as pd
+from scipy import stats
+from statsmodels.stats.multicomp import pairwise_tukeyhsd
+
+# Step 2: Load the ADaM dataset (from Experiment 6)
+advs = pd.read_csv('advs.csv')
+post = advs[advs['AVISIT'] == 'WEEK 12'].dropna(subset=['CHG']).copy()
+
+# Step 3: Descriptive statistics by group
+print(post.groupby('SEX')['CHG'].describe())
+print(post.groupby('AGEGR1')['CHG'].describe())
+
+# Step 4: Paired t-test - baseline vs. Week 12 systolic BP
+t_stat, p_val = stats.ttest_rel(post['BASE'], post['AVAL'])
+print("Paired t-test: t =", round(t_stat, 3), ", p =", round(p_val, 4))
+
+# Step 5: Independent t-test - change from baseline, male vs. female
+male = post.loc[post['SEX'] == 'M', 'CHG']
+female = post.loc[post['SEX'] == 'F', 'CHG']
+t_stat, p_val = stats.ttest_ind(male, female, equal_var=False)
+print("Independent t-test: t =", round(t_stat, 3), ", p =", round(p_val, 4))
+
+# Step 6: One-way ANOVA - change from baseline across age groups
+groups = [g['CHG'].values for _, g in post.groupby('AGEGR1')]
+f_stat, p_val = stats.f_oneway(*groups)
+print("ANOVA: F =", round(f_stat, 3), ", p =", round(p_val, 4))
+
+# Step 7: Post-hoc test (Tukey HSD) between age groups
+print(pairwise_tukeyhsd(post['CHG'], post['AGEGR1']))
+
+# Step 8: Interpret the results
+alpha = 0.05
+print("Significant at 5% level" if p_val < alpha else "Not significant at 5% level")

pc_123-0.1.0.dist-info/METADATA

@@ -0,0 +1,8 @@
+Metadata-Version: 2.4
+Name: pc-123
+Version: 0.1.0
+Summary: Lab experiment code viewer
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file

pc_123-0.1.0.dist-info/RECORD

@@ -0,0 +1,15 @@
+pc123/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+pc123/cli.py,sha256=6JUp2biY5VmSFrFwzjqThMP9j3APLLeMKLY2VPFVXQw,530
+pc123/experiments/exp1.py,sha256=EUj_2PARG6m_ampikz6FZJTfDiRFiahyGf7rOUM5YVQ,557
+pc123/experiments/exp2.py,sha256=daZm_sWS8JVV9rGoDS4Bp_h8OfinZQRtB514R_xiZao,771
+pc123/experiments/exp3.py,sha256=O5sROsmye_1Ba97M9fB2D03lN7e8itVC6YzrjSXvalE,1487
+pc123/experiments/exp4.py,sha256=LBeYsiP2uqRVY1kF1QpoCJGOvG1mCqWSspNsucRLHYM,1481
+pc123/experiments/exp5.py,sha256=kavlR8KNVC3v0xjEtMAsToSgyLQBHwxqJu9jS3s23-k,2126
+pc123/experiments/exp6.py,sha256=T17IF3bzZEfe3oz_MFvpWHCCl7JwN6RZfAimiAm8LHw,1801
+pc123/experiments/exp7.py,sha256=ubIA2FWwflJmtf_M8yTjUFwhOO9NfbDtXtdErLk3CBI,1415
+pc_123-0.1.0.dist-info/licenses/LICENSE,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+pc_123-0.1.0.dist-info/METADATA,sha256=oN5eO4-DwhSkKwQj_c2CDzrZ6XBvCvxIY0isCQ6CA90,201
+pc_123-0.1.0.dist-info/WHEEL,sha256=mOdXR9C3wMVov7cSY8PY-XCzo3SmmWCHvGQr5csJoao,91
+pc_123-0.1.0.dist-info/entry_points.txt,sha256=MmAoODyMpDaPnpZ5Dbb_KTC0SDksTV7dq0SGaybSAYo,42
+pc_123-0.1.0.dist-info/top_level.txt,sha256=MEdVBGA4U2YXsFUuLXpBXnGIvkzXGYuPqSatGpXrnSE,6
+pc_123-0.1.0.dist-info/RECORD,,

pc_123-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (84.2.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

pc_123-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+pc-123 = pc123.cli:main

pc_123-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+pc123