little polish

Author: frederikhoengaard

Pipfile

@@ -8,6 +8,7 @@ loguru = "==0.6.*"
 pandas = "==1.5.*"
 scikit-learn = "*"
 tqdm = "*"
+jupyter = "*"
 
 [dev-packages]
 black = "==23.*"

Pipfile.lock

@@ -1,4 +1,4 @@
-# lazy-learn
+![lazy-learn logo](docs/logo/transparent.png)
 0.0.1
 
 ---

README.md

@@ -1,3 +1,4 @@
+import pandas as pd
 from pandas import Series
 from pipeline.pipeline import IngestionPipeline
 from tqdm import tqdm
@@ -12,6 +13,7 @@ def apply(self, pipeline: IngestionPipeline):
         :param pipeline: parent IngestionPipeline
         :return:
         """
+        self.df = pipeline.df
         columns = pipeline.df.columns
         column_types = {}
 
@@ -37,7 +39,10 @@ def analyze_column(self, column: Series):
         elif self.numeric_test(types):
             return "numeric"
 
-        return "object"
+        elif self.datetime_check(column):
+            return "datetime"
+        else:
+            return "object"
 
     @staticmethod
     def categorical_test(values: list):
@@ -73,6 +78,9 @@ def numeric_test(types: list):
     def string_test(types: set):
         raise NotImplementedError
 
-    @staticmethod
-    def date_check(types: set):
-        raise NotImplementedError
+    def datetime_check(self, column: Series):
+        try:
+            self.df[column.name] = pd.to_datetime(column)
+            return True
+        except:
+            return False

doc/logo/grayscale_transparent.png

@@ -1,7 +1,15 @@
+from pandas import DataFrame
+
+
 class Dataset:
-    def __init__(self):
+    def __init__(self, df: DataFrame, column_type_map: dict):
         self.name = None
         self.description = None
+        self.df = df
+        self.column_type_map = column_type_map
+
+    def save(self):
+        raise NotImplementedError
 
 
 class Model:

doc/logo/original.png

@@ -31,4 +31,4 @@ def __init__(self):
         self.summary_stats: dict = {}
 
     def response(self):
-        return Dataset
+        return Dataset(df=self.df, column_type_map=self.column_type_map)