opsci-toolbox 0.0.16__py3-none-any.whl → 0.0.17__py3-none-any.whl

opsci_toolbox/helpers/common.py

@@ -1502,6 +1502,28 @@ def custom_ordering(df : pd.DataFrame, col_to_order : str, custom_order : list)
     df[col_to_order] = pd.Categorical(df[col_to_order], categories=custom_order, ordered=True).to_numpy()
     return df
 
+# def calcul_total_et_pourcentage(df : pd.DataFrame, col_gb : list, metrics : dict) -> pd.DataFrame:
+#     """
+#     Calculates the total and percentage values for the given metrics based on a grouping column.
+#     Args:
+#         df (DataFrame): The input DataFrame.
+#         col_gb (list):  Names of the columns to group by.
+#         metrics (dict): A dictionary of metrics to calculate.
+#     Returns:
+#         DataFrame: The modified DataFrame with total and percentage values added.
+
+#     """
+#     percentage_agregations = {f'per_{key}': lambda x: x[key] / x[f"total_{key}"] for key in list(metrics.keys())}
+
+#     df = (df.join(df.groupby(col_gb)
+#                   .agg(metrics)
+#                   .add_prefix("total_"), on=col_gb
+#                   )
+#                 .assign(**percentage_agregations).fillna(0)
+#         )
+    
+#     return df
+
 def calcul_total_et_pourcentage(df : pd.DataFrame, col_gb : list, metrics : dict) -> pd.DataFrame:
     """
     Calculates the total and percentage values for the given metrics based on a grouping column.
@@ -1513,14 +1535,15 @@ def calcul_total_et_pourcentage(df : pd.DataFrame, col_gb : list, metrics : dict
         DataFrame: The modified DataFrame with total and percentage values added.
 
     """
-    percentage_agregations = {f'per_{key}': lambda x: x[key] / x[f"total_{key}"] for key in list(metrics.keys())}
+    # percentage_agregations = {f'per_{key}': lambda x: x[key] / x[f"total_{key}"] for key in list(metrics.keys())}
 
     df = (df.join(df.groupby(col_gb)
                   .agg(metrics)
                   .add_prefix("total_"), on=col_gb
                   )
-                .assign(**percentage_agregations).fillna(0)
         )
-    
-    return df
+    for key in list(metrics.keys()):
+        df['per_' + key] = df[key] / df['total_' + key]
+        df['per_' + key] = df['per_' + key].fillna(0)
 
+    return df

opsci_toolbox/helpers/dataviz.py

@@ -2007,6 +2007,115 @@ def horizontal_stacked_bars(df: pd.DataFrame,
     
     return fig
 
+def bar_stacked(df: pd.DataFrame,
+                             col_x: str,
+                             col_y: str,
+                             col_cat: str,
+                             col_color: str,
+                             **kwargs) -> go.Figure:
+    """
+    Create horizontal stacked bar plots.
+
+    Args:
+        df (pd.DataFrame): DataFrame containing data for the bar plots.
+        col_x (str): Name of the column containing x-axis values.
+        col_y (str): Name of the column containing y-axis values.
+        col_percentage (str): Name of the column containing percentage values.
+        col_cat (str): Name of the column containing categories.
+        col_color (str): Name of the column containing colors.
+        **kwargs: Additional keyword arguments to update default plotting parameters.
+
+    Returns:
+        go.Figure: Plotly Figure object representing the horizontal stacked bar plots.
+    """
+    params = general_kwargs()
+    params.update(kwargs)
+
+    categories = df[col_cat].unique()
+
+    col_hover = params["col_hover"]
+
+    fig = go.Figure()
+    
+    for cat in categories:
+        current_df = df[df[col_cat] == cat]
+        hovertemplate= "<b>Catégorie</b> : "+str(cat)+"<br><b>"+str(col_x)+"</b> : "+current_df[col_x].astype(str)+ str(col_y) + "</b> : "+current_df[col_y].astype(str)
+
+        for c in col_hover:
+            hovertemplate += (
+                "<br><b>"
+                + str(c)
+                + "</b>:"
+                + current_df[c].astype(str).apply(wrap_text)
+            )
+
+        fig.add_trace(
+            go.Bar(
+                x=current_df[col_x], 
+                y=current_df[col_y],
+                orientation=params['orientation'],
+                text = current_df[col_x],
+                textposition=params["textposition"],
+                name=cat, 
+                marker=dict(color=current_df[col_color]),
+                hovertemplate=hovertemplate+'<extra></extra>',
+                textangle=params["xaxis_tickangle"],
+                )
+        )
+
+    fig.update_layout(
+            barmode='stack',
+            title_text=params["title_text"], 
+            showlegend=params['showlegend'],
+            width = params["width"],
+            height= params["height"],
+            font_family=params["font_family"],
+            font_size=params["font_size"],
+            template=params["template"],
+            plot_bgcolor=params["plot_bgcolor"],  # background color (plot)
+            paper_bgcolor=params["paper_bgcolor"],
+            uniformtext_minsize=params["uniformtext_minsize"],
+            uniformtext_mode=params["uniformtext_mode"],
+
+        )
+    
+    fig.update_yaxes(
+        # title=params["yaxis_title"],
+        title_font_size=params["yaxis_title_font_size"],
+        tickangle=params["yaxis_tickangle"],
+        tickfont_size=params["yaxis_tickfont_size"],
+        range=params["yaxis_range"],
+        showgrid=params["yaxis_showgrid"],
+        showline=params["yaxis_showline"],
+        zeroline=params["yaxis_zeroline"],
+        gridwidth=params["yaxis_gridwidth"],
+        gridcolor=params["yaxis_gridcolor"],
+        linewidth=params["yaxis_linewidth"],
+        linecolor=params["yaxis_linecolor"],
+        mirror=params["yaxis_mirror"],
+    )
+
+    fig.update_xaxes(
+        # title=params["xaxis_title"],
+        title_font_size=params["xaxis_title_font_size"],
+        tickangle=params["xaxis_tickangle"],
+        tickfont_size=params["xaxis_tickfont_size"],
+        # range=params["xaxis_range"],
+        showgrid=params["xaxis_showgrid"],
+        showline=params["xaxis_showline"],
+        zeroline=params["xaxis_zeroline"],
+        gridwidth=params["xaxis_gridwidth"],
+        gridcolor=params["xaxis_gridcolor"],
+        linewidth=params["xaxis_linewidth"],
+        linecolor=params["xaxis_linecolor"],
+        mirror=params["xaxis_mirror"]
+    )
+    fig.update_xaxes(title_text=params["xaxis_title"])
+    fig.update_yaxes(title_text=params["yaxis_title"])
+    fig.update_yaxes(showticklabels = False)
+    
+    return fig
+
 def bar_trend_per_cat(df: pd.DataFrame, 
                               col_x: str, 
                               col_cat: str, 
@@ -3597,13 +3706,11 @@ def density_map(df_posts: pd.DataFrame,
                 show_topics: bool = True,
                 show_halo: bool = False,
                 show_histogram: bool = True,
-
                 colorscale: str = "Portland",
                 marker_color: str = "#ff7f0e",
                 arrow_color: str = "#ff7f0e",
                 width: int = 1000,
                 height: int = 1000,
-                
                 label_size_ratio: int = 100,
                 n_words: int = 3,
                 title_text: str = "Clustering",
@@ -3625,7 +3732,7 @@ def density_map(df_posts: pd.DataFrame,
         col_engagement (str): Column name corresponding to a metric.
         col_text (str): Column name corresponding to a text separated by |.
         col_text_dots (str): Column name corresponding to the text for dots.
-        colorscale (str, optional): Possible values are 'https://plotly.com/python/builtin-colorscales/'. Defaults to "Portland".
+        colorscale (str, optional): Possible values are ``https://plotly.com/python/builtin-colorscales/``. Defaults to "Portland".
         marker_color (str, optional): Dots color value. Defaults to "#ff7f0e".
         arrow_color (str, optional): Arrow pointing to topic centroid color value. Defaults to "#ff7f0e".
         width (int, optional): Width of the plot. Defaults to 1000.

opsci_toolbox/helpers/nlp.py

@@ -2074,9 +2074,9 @@ def encode_chunked_files(chunk_files_paths: list,
     Encode text from files and save the results in another pickle file.
     
     Parameters:
-        chunk_files_paths (List[str]): List of file paths containing documents.
+        chunk_files_paths (list): List of file paths containing documents.
         HF_encoder (Encoder): Encoder object for text vectorization.
-        cols (List[str]): Columns to keep in the resulting DataFrame.
+        cols (list): Columns to keep in the resulting DataFrame.
         col_text (str): Column containing text data in the DataFrame.
         path_embedded_chunks (str): Path to save the embedded chunks.
         reencode (bool, optional): Whether to re-encode files even if they already exist. Defaults to False.
@@ -2118,12 +2118,10 @@ def encode_labels(data_to_encode: np.ndarray) -> tuple:
     Encodes a list of labels using a LabelEncoder.
 
     Args:
-    - data_to_encode (List[Union[str, int]]): The list of labels to encode. Labels can be of any hashable type, 
-      but strings or integers are typical.
+        data_to_encode (List[Union[str, int]]): The list of labels to encode. Labels can be of any hashable type, but strings or integers are typical.
 
     Returns:
-    - Tuple[LabelEncoder, np.ndarray]: A tuple containing the fitted LabelEncoder instance and a numpy array 
-      of encoded labels.
+        Tuple[LabelEncoder, np.ndarray]: A tuple containing the fitted LabelEncoder instance and a numpy array of encoded labels.
     """
     label_encoder = LabelEncoder()
     label_encoder.fit(data_to_encode)
@@ -2150,12 +2148,10 @@ def one_hot_encode(data_to_encode:np.ndarray) -> tuple:
     One-hot encodes a list of categorical values using OneHotEncoder.
 
     Args:
-    - data_to_encode (List[Union[str, int]]): The list of categorical values to encode. The values can be of 
-      any hashable type, typically strings or integers.
+    - data_to_encode (List[Union[str, int]]): The list of categorical values to encode. The values can be of any hashable type, typically strings or integers.
 
     Returns:
-    - Tuple[OneHotEncoder, np.ndarray]: A tuple containing the fitted OneHotEncoder instance and a numpy array 
-      of one-hot encoded values.
+    - Tuple[OneHotEncoder, np.ndarray]: A tuple containing the fitted OneHotEncoder instance and a numpy array of one-hot encoded values.
     """
     one_hot_encoder = OneHotEncoder(sparse=False)
     data_to_encode_reshaped = np.array(data_to_encode).reshape(-1, 1)  # Reshape for OneHotEncoder

opsci_toolbox/helpers/nlp_cuml.py

@@ -258,7 +258,7 @@ def process_UMAP(embedded_chunks_paths: list, path_reduced_embeddings_id: str, r
     new_file_paths=[]
     for file_path in tqdm(embedded_chunks_paths, total=len(embedded_chunks_paths), desc="UMAP transform from files"):
         
-        filename = os.path.splitext(os.path.basename(file_path))[0][:-9]
+        filename = os.path.splitext(os.path.basename(file_path))[0]
         new_filename = filename+"_reduce_embeddings.parquet"
         new_file_path = os.path.join(path_reduced_embeddings_id, new_filename)
     
@@ -309,7 +309,7 @@ def process_HDBSCAN(clusterer,
     new_file_paths=[]
     for file_path in tqdm(reduced_embeddings_paths, total=len(reduced_embeddings_paths), desc="HDBSCAN transform from files"):
         
-        filename = os.path.splitext(os.path.basename(file_path))[0][:-18]
+        filename = os.path.splitext(os.path.basename(file_path))[0]
         new_filename = filename+ "_predictions.parquet"
         new_file_path = os.path.join(path_predictions_dataset_id, new_filename)
         if not os.path.exists(new_file_path) or reencode:
@@ -566,7 +566,7 @@ def cudf_write_parquet(df: cudf.DataFrame, path: str, filename: str) -> str:
     df.to_parquet(file_path)
     return file_path
 
-def cudf_read_parquet(path: str) -> cudf.DataFrame:
+def cudf_read_parquet(path: str, cols : list = None) -> cudf.DataFrame:
     """
     Read a Parquet file into a cuDF DataFrame.
 
@@ -576,7 +576,10 @@ def cudf_read_parquet(path: str) -> cudf.DataFrame:
     Returns:
         cudf.DataFrame: The read cuDF DataFrame.
     """
-    df = cudf.read_parquet(path)
+    if cols : 
+        df = cudf.read_parquet(path, columns=cols)
+    else :
+        df = cudf.read_parquet(path)
     return df 
 
 def convert_df_to_cudf(df: pd.DataFrame) -> cudf.DataFrame:

opsci_toolbox/helpers/sna.py

@@ -44,7 +44,7 @@ def create_subgraph_min_metric(G: nx.Graph, metric: str = "degree", min_value: f
     
     subgraph = G.subgraph(nodes_with_min_metric).copy()
     return subgraph
-
+    
 def group_nodes_by_values(dictionnary : dict) -> dict:
     """
     Group nodes by their values from a dictionary.

{opsci_toolbox-0.0.16.dist-info → opsci_toolbox-0.0.17.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: opsci-toolbox
-Version: 0.0.16
+Version: 0.0.17
 Summary: a complete toolbox
 Home-page: UNKNOWN
 Author: Erwan Le Nagard

{opsci_toolbox-0.0.16.dist-info → opsci_toolbox-0.0.17.dist-info}/RECORD

@@ -6,21 +6,21 @@ opsci_toolbox/apis/telegram.py,sha256=JjmAk6tKvpnFIYpZDKthxS_mgqhWQpDPUOvyC7SiWP
 opsci_toolbox/apis/webscraping.py,sha256=fo6H2OaH0m_LHJB9IyN-q0Vkk8L9OvHxNn4O_A6a6yc,21572
 opsci_toolbox/apis/youtube_helpers.py,sha256=j4hwCS2BEWRJjd9Q5XBN9FeCrL3lqteyz5dqbtfypdo,17418
 opsci_toolbox/helpers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-opsci_toolbox/helpers/common.py,sha256=zmi-FbN39Rci_hGEKj2bmkcucrVwnHhMgKU6AAIap3Q,53327
+opsci_toolbox/helpers/common.py,sha256=gM0QzLsdjMQTTT522CqzpFO86YWaxPaK48EXemjw9nI,54298
 opsci_toolbox/helpers/cv.py,sha256=N3hnLX223UQbdw_YEdUYj10xUXT_95O6BpQt6TbAE08,21092
-opsci_toolbox/helpers/dataviz.py,sha256=U2Kj-xoF1wHvYXUKxLsrSvKnhky9PrPUy61s1WEKp44,208743
+opsci_toolbox/helpers/dataviz.py,sha256=viIrTrnxFzCRLY5sJDEz3jJtsB-gZTZb2uLoq0yvTlU,212762
 opsci_toolbox/helpers/dates.py,sha256=Pq-SKP2n1z0_jzU8NxGSv8CHLH_MOKjP_rNYeny0Tb8,4752
 opsci_toolbox/helpers/gliner.py,sha256=qLkpuoCDezQyYmg_TE3XYETSpobHods6WBjCLo0Gjqw,3579
-opsci_toolbox/helpers/nlp.py,sha256=4edA5JZ4vzpU4U9w-INNspW2oTQ-yYpm5rFXExKB4YI,108324
-opsci_toolbox/helpers/nlp_cuml.py,sha256=KfgC0hMqLCKoOME2DOu3Wje4ormV19fEB8Fyq8G7D-E,30901
-opsci_toolbox/helpers/sna.py,sha256=3qx1WBQwLKpZNGR0bLSMB2-LBRx-vtNHp8puzoj-84A,33730
+opsci_toolbox/helpers/nlp.py,sha256=MC2ibMi0j9BCysloEPXpvpvRlzlMvRn8krOAcFF-4VU,108286
+opsci_toolbox/helpers/nlp_cuml.py,sha256=sLvaDfVL0aoGi3mNXUkW47tWVrrYK5wxbf8QPgljQNA,30991
+opsci_toolbox/helpers/sna.py,sha256=yzBTQXYXow_lKGhlSMz8hYl2JcSlle95YEDht9v-_fY,33734
 opsci_toolbox/helpers/sql.py,sha256=LMrDWcv1QpfE8HyyrqiKuhhkt930lvME3-AKU89LF38,1928
 opsci_toolbox/helpers/surreaction.py,sha256=JjVvHs7Sf9IJxX0QdHpQ_3E8-c_OS6q_bfUKvurl1z4,7093
 opsci_toolbox/lexicons/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 opsci_toolbox/lexicons/stop_words_en.csv,sha256=4lzjBZHCn_b3lg_CUNkmA_MDQ7DLEpS83k6-dWpkC2o,1957
 opsci_toolbox/lexicons/stop_words_fr.csv,sha256=sPdA8VmyNYbiHg-M8O3tg7ayHvCE3GDg6cF-oSZxICM,6776
-opsci_toolbox-0.0.16.dist-info/METADATA,sha256=-SCFUBnwnWlUrOGgQwxib8ZfCjWxXm3iVVwnfErQ9Fk,1727
-opsci_toolbox-0.0.16.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-opsci_toolbox-0.0.16.dist-info/dependency_links.txt,sha256=bEiJsgyh9M0F_pGpJBwUYDefiTNq9F6QEGfQS5RH1Os,39
-opsci_toolbox-0.0.16.dist-info/top_level.txt,sha256=fUiqxou4FPec_tOfauTLCKAuepeYLfRyhedycWxVnq4,14
-opsci_toolbox-0.0.16.dist-info/RECORD,,
+opsci_toolbox-0.0.17.dist-info/METADATA,sha256=RvPoecg-cflzmh0PcNj9dDZm_RLp5KsK2n-hRTXdEUs,1727
+opsci_toolbox-0.0.17.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+opsci_toolbox-0.0.17.dist-info/dependency_links.txt,sha256=bEiJsgyh9M0F_pGpJBwUYDefiTNq9F6QEGfQS5RH1Os,39
+opsci_toolbox-0.0.17.dist-info/top_level.txt,sha256=fUiqxou4FPec_tOfauTLCKAuepeYLfRyhedycWxVnq4,14
+opsci_toolbox-0.0.17.dist-info/RECORD,,