validmind 1.7.0__py3-none-any.whl → 1.8.1__py3-none-any.whl

validmind/datasets/classification/{taiwan_credit.pyx → taiwan_credit.py}

@@ -11,7 +11,7 @@ from . import (
 )
 
 current_path = os.path.dirname(os.path.abspath(__file__))
-dataset_path = os.path.join(current_path, "..", "..", "..", "notebooks", "datasets")
+dataset_path = os.path.join(current_path, "datasets")
 
 drop_columns = ["ID"]
 boolean_columns = ["SEX"]

validmind/datasets/regression/__init__.py

@@ -1,3 +1,57 @@
 """
-Entrypoint to Model Evaluation API
+Entrypoint for regression datasets
 """
+import pandas as pd
+
+
+def identify_frequencies(df):
+    """
+    Identify the frequency of each series in the DataFrame.
+
+    :param df: Time-series DataFrame
+    :return: DataFrame with two columns: 'Variable' and 'Frequency'
+    """
+    frequencies = []
+    for column in df.columns:
+        series = df[column].dropna()
+        if not series.empty:
+            freq = pd.infer_freq(series.index)
+            if freq == "MS" or freq == "M":
+                label = "Monthly"
+            elif freq == "Q":
+                label = "Quarterly"
+            elif freq == "A":
+                label = "Yearly"
+            else:
+                label = freq
+        else:
+            label = None
+
+        frequencies.append({"Variable": column, "Frequency": label})
+
+    freq_df = pd.DataFrame(frequencies)
+
+    return freq_df
+
+
+def resample_to_common_frequency(df, common_frequency="MS"):
+    # Make sure the index is a datetime index
+    if not isinstance(df.index, pd.DatetimeIndex):
+        df.index = pd.to_datetime(df.index)
+
+    # Create an empty DataFrame to store the resampled data
+    resampled_df = pd.DataFrame()
+
+    # Iterate through each variable and resample it to the common frequency
+    for column in df.columns:
+        series = df[column].dropna()
+        inferred_freq = pd.infer_freq(series.index)
+
+        if inferred_freq is None or inferred_freq != common_frequency:
+            resampled_series = df[column].resample(common_frequency).interpolate()
+        else:
+            resampled_series = df[column]
+
+        resampled_df[column] = resampled_series
+
+    return resampled_df