pandas-plots 0.9.5__tar.gz → 0.9.7__tar.gz

{pandas-plots-0.9.5/src/pandas_plots.egg-info → pandas-plots-0.9.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pandas-plots
-Version: 0.9.5
+Version: 0.9.7
 Summary: A collection of helper for table handling and vizualization
 Home-page: https://github.com/smeisegeier/pandas-plots
 Author: smeisegeier

{pandas-plots-0.9.5 → pandas-plots-0.9.7}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = pandas-plots
-version = 0.9.5
+version = 0.9.7
 author = smeisegeier
 author_email = dexterDSDo@googlemail.com
 description = A collection of helper for table handling and vizualization

{pandas-plots-0.9.5 → pandas-plots-0.9.7}/src/pandas_plots/hlp.py

@@ -179,15 +179,23 @@ def create_barcode_from_url(
     output_path: str | None = None,
     show_image: bool = False,
 ):
+    """
+    Create a barcode from the given URL. Uses "QR Code" from DENSO WAVE INCORPORATED.
+
+    Args:
+        url (str): The URL to encode in the barcode.
+        output_path (str | None, optional): The path to save the barcode image. Defaults to None.
+        show_image (bool, optional): Whether to display the barcode image. Defaults to False.
+    """
     WIDTH = 400
     HEIGHT = 400
 
     if not re.match(URL_REGEX, url):
-        print("❌ Not a valid URL")
-        return
+        print("💡 Not a valid URL")
 
     image = requests.get(
-        f"https://chart.googleapis.com/chart?chs={WIDTH}x{HEIGHT}&cht=qr&chl={url}"
+        # f"https://chart.googleapis.com/chart?chs={WIDTH}x{HEIGHT}&cht=qr&chl={url}"
+        f"https://api.qrserver.com/v1/create-qr-code/?size={WIDTH}x{HEIGHT}&data={url}"
     )
     image.raise_for_status()
 
@@ -202,3 +210,34 @@ def create_barcode_from_url(
         plt.imshow(img)
         # plt.axis('off')  # Turn off axis numbers
         plt.show()
+
+def add_datetime_columns(df: pd.DataFrame, date_column: str = None) -> pd.DataFrame:
+    if not date_column:
+        date_column = [col for col in df.columns if pd.api.types.is_datetime64_any_dtype(df[col])][0]
+
+    if not date_column or not pd.api.types.is_datetime64_any_dtype(df[date_column]):
+        print("❌ No datetime column found")
+        return
+    
+    if [col for col in df.columns if "YYYY-WW" in col]:
+        print("❌ Added datetime columns already exist")
+        return
+    
+    print(f"⏳ Adding datetime columns basing off of: {date_column}")
+    df_= df.copy()
+
+    df_[date_column] = pd.to_datetime(df_[date_column])
+
+    df_["YYYY"] = df_[date_column].dt.year
+    df_["MM"] = df_[date_column].dt.month
+    df_["Q"] = df_[date_column].dt.quarter
+
+    df_["YYYY-MM"] = df_[date_column].dt.to_period("M").astype(str)
+    df_["YYYYQ"] = df_[date_column].dt.to_period("Q").astype(str)
+    df_["YYYY-WW"] = (
+        df_[date_column].dt.isocalendar().year.astype(str) + "-" +
+        df_[date_column].dt.isocalendar().week.astype(str).str.zfill(2)
+    )
+    df_["DDD"] = df_[date_column].dt.weekday.map({0: "Mon", 1: "Tue", 2: "Wed", 3: "Thu", 4: "Fri", 5: "Sat", 6: "Sun"})
+    
+    return df_

{pandas-plots-0.9.5 → pandas-plots-0.9.7}/src/pandas_plots/pls.py

@@ -111,6 +111,7 @@ def plot_stacked_bars(
     caption: str = None,
     sort_values: bool = False,
     show_total: bool = False,
+    precision: int = 0,
 ) -> None:
     """
     Generates a stacked bar plot using the provided DataFrame.
@@ -135,6 +136,7 @@ def plot_stacked_bars(
     - caption: An optional string indicating the caption for the chart.
     - sort_values: bool = False - Sort axis by index (default) or values
     - show_total: bool = False - Whether to show the total value
+    - precision: int = 0 - The number of decimal places to round to
 
     Returns:
     None
@@ -166,6 +168,9 @@ def plot_stacked_bars(
         df.iloc[:, 0] = df.iloc[:, 0].str.strip()
     if df.iloc[:, 1].dtype.kind == "O":
         df.iloc[:, 1] = df.iloc[:, 1].str.strip()
+    
+    # * apply precision
+    df.iloc[:,2] = df.iloc[:,2].round(precision)
 
     # * set index + color col
     col_index = df.columns[0] if not swap else df.columns[1]
@@ -523,7 +528,7 @@ def plot_bars(
             },
         },
         showlegend=False,
-        uniformtext_minsize=14, uniformtext_mode='hide'
+        # uniformtext_minsize=14, uniformtext_mode='hide'
         
     )
     # * sorting

{pandas-plots-0.9.5 → pandas-plots-0.9.7}/src/pandas_plots/tbl.py

@@ -14,10 +14,10 @@ from plotly.subplots import make_subplots
 from scipy import stats
 
 from .hlp import wrap_text
-from devtools import debug
+# from devtools import debug
+pd.options.display.colheader_justify = "right"
 # pd.options.mode.chained_assignment = None
 
-
 TOTAL_LITERAL = Literal[
     "sum", "mean", "median", "min", "max", "std", "var", "skew", "kurt"
 ]
@@ -36,6 +36,7 @@ def describe_df(
     sort_mode: Literal["value", "index"] = "value",
     top_n_uniques: int = 30,
     top_n_chars_in_index: int = 0,
+    top_n_chars_in_columns: int = 0,
 ):
     """
     This function takes a pandas DataFrame and a caption as input parameters and prints out the caption as a styled header, followed by the shape of the DataFrame and the list of column names. For each column, it prints out the column name, the number of unique values, and the column data type. If the column is a numeric column with more than 100 unique values, it also prints out the minimum, mean, maximum, and sum values. Otherwise, it prints out the first 100 unique values of the column.
@@ -52,6 +53,7 @@ def describe_df(
     sort_mode (Literal["value", "index"]): sort by value or index
     top_n_uniques (int): number of uniques to display
     top_n_chars_in_index (int): number of characters to display on plot axis
+    top_n_chars_in_columns (int): number of characters to display on plot axis. If set, minimum is 10.
 
     usage:
     describe_df(
@@ -75,6 +77,11 @@ def describe_df(
         print(f"DataFrame is empty!")
         return
 
+    # ! fix bug(?) in plotly - empty float columns are not plotted, set these to str
+    for col in df.columns:
+        if df[col].notna().sum() == 0 and df[col].dtype == "float":
+            df[col] = df[col].astype(str)
+
     print(f"🔵 {'*'*3} df: {caption} {'*'*3}")
     print(f"🟣 shape: ({df.shape[0]:_}, {df.shape[1]}) columns: {df.columns.tolist()} ")
     print(f"🟣 duplicates: {df.duplicated().sum():_}")
@@ -123,6 +130,15 @@ def describe_df(
     # ! *** PLOTS ***
     if not use_plot:
         return
+    
+    # * reduce column names len if selected
+    if top_n_chars_in_columns > 0:
+        # * minumum 10 chars, or display is cluttered
+        top_n_chars_in_columns = 10 if top_n_chars_in_columns < 10 else top_n_chars_in_columns
+        col_list = []
+        for i, col in enumerate(df.columns):
+            col_list.append(col[:top_n_chars_in_columns]+"_"+str(i).zfill(3))
+        df.columns = col_list
 
     # * respect fig_offset to exclude unwanted plots from maintanance columns
     cols = df.iloc[:, :fig_offset].columns
@@ -167,6 +183,7 @@ def describe_df(
                     else s[:top_n_chars_in_index]
                 )
                 x = [_cut(item) for item in x]
+            
             figsub = px.bar(
                 x=x,
                 y=y,
@@ -346,7 +363,7 @@ def show_num_df(
     """
     # * ensure arguments match parameter definition
     if any([df[col].dtype.kind not in ["i", "u", "f"] for col in df.columns]) == True:
-        print(f"❌ table must contain numeric data only")
+        print(f"❌ table must contain numeric data only. Maybe you forgot to convert this table with pivot or pivot_table first?")
         return
 
     if (

{pandas-plots-0.9.5 → pandas-plots-0.9.7/src/pandas_plots.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pandas-plots
-Version: 0.9.5
+Version: 0.9.7
 Summary: A collection of helper for table handling and vizualization
 Home-page: https://github.com/smeisegeier/pandas-plots
 Author: smeisegeier