z230

CTMS/VisitsFromCTMSExport/10_explore_data.py

@@ -0,0 +1,47 @@
+import pandas as pd
+
+CSV_FILE = "filename.csv"
+
+df = pd.read_csv(CSV_FILE, sep=";", encoding="utf-8-sig")
+
+# Parse dates
+date_cols = ["Original Due Date", "Due Date", "Window Start Date", "Cutoff Date", "Completed Date"]
+for col in date_cols:
+    df[col] = pd.to_datetime(df[col], errors="coerce")
+
+# Country from site number
+df["Country"] = df["Study Site Number"].str.extract(r"DD5-([A-Z]+)\d+")
+
+print("=" * 60)
+print("CTMS VISITS EXPORT — přehled dat")
+print("=" * 60)
+print(f"\nCelkem řádků : {len(df):,}")
+print(f"Celkem sloupců: {len(df.columns)}")
+print(f"\nSloupce:\n  " + "\n  ".join(df.columns.tolist()))
+
+print(f"\nSites celkem : {df['Study Site Number'].nunique()}")
+print(f"Zemí celkem  : {df['Country'].nunique()}")
+print(f"Země         : {', '.join(sorted(df['Country'].dropna().unique()))}")
+
+print("\nStatus:")
+for k, v in df["Status"].value_counts().items():
+    print(f"  {k:<20} {v:>6,}")
+
+print("\nCategory:")
+for k, v in df["Category"].value_counts().items():
+    print(f"  {k:<25} {v:>6,}")
+
+print("\nSub Category:")
+for k, v in df["Sub Category"].value_counts().items():
+    print(f"  {k:<20} {v:>6,}")
+
+print(f"\nReference kódy: {sorted(df['Reference'].dropna().unique().tolist())}")
+
+print("\nRozsah dat:")
+for col in ["Due Date", "Completed Date"]:
+    vals = df[col].dropna()
+    if len(vals):
+        print(f"  {col:<20} {vals.min().date()} — {vals.max().date()}")
+
+print("\nNáhled (5 řádků):")
+print(df.head(5).to_string())