Sample code for the article on YData (#743)

* Sample code for the article on YData

* Linter issues

Author: lpozo

ydata-profiling/README.md

@@ -0,0 +1,3 @@
+# Automate Python Data Analysis With YData Profiling
+
+This folder provides the code examples for the Real Python tutorial [Automate Python Data Analysis With YData Profiling](https://realpython.com/ydata-profiling-eda/).

ydata-profiling/airport_comparison.py

@@ -0,0 +1,14 @@
+import pandas as pd
+from ydata_profiling import ProfileReport
+
+df = pd.read_csv("flight_data_2024_sample.csv")
+
+# Split into flights originating from LAX and ATL
+df_lax = df[df["origin"] == "LAX"]
+df_atl = df[df["origin"] == "ATL"]
+
+lax_profile = ProfileReport(df_lax, title="LAX Flights")
+atl_profile = ProfileReport(df_atl, title="ATL Flights")
+
+comparison = lax_profile.compare(atl_profile)
+comparison.to_file("airport_comparison.html")

ydata-profiling/flight_data_2024_sample.csv

@@ -0,0 +1,7 @@
+import pandas as pd
+from ydata_profiling import ProfileReport
+
+df = pd.read_csv("flight_data_2024_sample.csv")
+
+profile = ProfileReport(df)
+profile.to_file("flight_report.html")

ydata-profiling/flight_report_v1.py

@@ -0,0 +1,16 @@
+import pandas as pd
+from ydata_profiling import ProfileReport
+
+df = pd.read_csv("flight_data_2024_sample.csv")
+
+profile = ProfileReport(
+    df,
+    variables={
+        "descriptions": {
+            "origin": "Airport code where the flight originated",
+            "dest": "Airport code of flight destination",
+            "crs_dep_time": "Scheduled departure time at origin (hhmm)",
+        }
+    },
+)
+profile.to_file("documented_report.html")

ydata-profiling/flight_report_v2.py

@@ -0,0 +1,13 @@
+import pandas as pd
+from ydata_profiling import ProfileReport
+
+df = pd.read_csv("flight_data_2024_sample.csv")
+
+# Option 1: Generate a minimal report
+profile = ProfileReport(df, minimal=True)
+profile.to_file("minimal_report.html")
+
+# Option 2: Sample your data before profiling
+df_sample = df.sample(n=10000, random_state=42)
+profile = ProfileReport(df_sample)
+profile.to_file("sampled_report.html")

ydata-profiling/flight_report_v3.py

@@ -0,0 +1,13 @@
+import pandas as pd
+from ydata_profiling import ProfileReport
+
+df = pd.read_csv("flight_data_2024_sample.csv")
+df["fl_date"] = pd.to_datetime(df["fl_date"])
+
+profile = ProfileReport(
+    df,
+    title="Flight Delay Report",
+    tsmode=True,
+    sortby="fl_date",
+)
+profile.to_file("flight_timeseries_report.html")