imsciences 0.6.2.5__py3-none-any.whl → 0.6.2.7__py3-none-any.whl

imsciences/datafunctions.py

@@ -109,13 +109,13 @@ class dataprocessing:
         
         print("\n17. pivot_table")
         print("    - Description: Dynamically pivots a DataFrame based on specified columns.")
-        print("    - Usage: pivot_table(df, index_col, columns, values_col, filters_dict=None, fill_value=0,aggfunc='sum',margins=False,margins_name='Total',datetime_trans_needed=True,reverse_header_order = 'False')")
-        print("    - Example: pivot_table(df, 'OBS', 'Channel Short Names', 'Value',filters_dict={'Master Include':' == 1','OBS':' >= datetime(2019,9,9)','Metric Short Names':' == 'spd''}, fill_value=0,aggfunc='sum',margins=False,margins_name='Total',datetime_trans_needed=True,reverse_header_order = 'True')")
+        print("    - Usage: pivot_table(df, index_col, columns, values_col, filters_dict=None, fill_value=0,aggfunc='sum',margins=False,margins_name='Total',datetime_trans_needed=True,reverse_header_order = 'False',fill_missing_weekly_dates=False,week_commencing='W-MON')")
+        print("    - Example: pivot_table(df, 'OBS', 'Channel Short Names', 'Value',filters_dict={'Master Include':' == 1','OBS':' >= datetime(2019,9,9)','Metric Short Names':' == 'spd''}, fill_value=0,aggfunc='sum',margins=False,margins_name='Total',datetime_trans_needed=True,reverse_header_order = 'True',fill_missing_weekly_dates=True,week_commencing='W-MON')")
         
         print("\n18. apply_lookup_table_for_columns")
         print("    - Description: Equivalent of xlookup in excel. Allows you to map a dictionary of substrings within a column. If multiple columns are need for the LUT then a | seperator is needed.")
-        print("    - Usage: classify_within_column(df, col_names, to_find_dict, if_not_in_country_dict='Other'), new_column_name='Mapping'")
-        print("    - Example: classify_within_column(df, ['campaign type','media type'], {'France Paid Social FB|paid social': 'facebook','France Paid Social TW|paid social': 'twitter'}, 'other','mapping')")
+        print("    - Usage: apply_lookup_table_for_columns(df, col_names, to_find_dict, if_not_in_dict='Other', new_column_name='Mapping')")
+        print("    - Example: apply_lookup_table_for_columns(df, col_names, {'spend':'spd','clicks':'clk'}, if_not_in_dict='Other', new_column_name='Metrics Short')")
 
         print("\n19. aggregate_daily_to_wc_wide")
         print("   - Description: Aggregates daily data into weekly data, grouping and summing specified columns, starting on a specified day of the week.")
@@ -226,6 +226,16 @@ class dataprocessing:
         print("    - Description: With two matching dataset, it takes the common columns and rows and takes the difference between them, outputing a differences and total differences table")
         print("    - Usage: compare_overlap(df1, df2, date_col)")
         print("    - Example: compare_overlap(df_1, df_2, 'obs')")        
+
+        print("\n41. week_commencing_2_week_commencing_conversion")
+        print("    - Description: Take a week commencing column say sunday and creates a new column with a different week commencing e.g. monday")
+        print("    - Usage: week_commencing_2_week_commencing_conversion(df,date_col,week_commencing='sun')")
+        print("    - Example: week_commencing_2_week_commencing_conversion(df,'obs,week_commencing='mon')")          
+
+        print("\n42. week_commencing_2_week_commencing_conversion")
+        print("    - Description: Take a week commencing column say sunday and creates a new column with a different week commencing e.g. monday")
+        print("    - Usage: week_commencing_2_week_commencing_conversion(df,date_col,week_commencing='sun')")
+        print("    - Example: week_commencing_2_week_commencing_conversion(df,'obs,week_commencing='mon')")           
         
         
                 
@@ -664,7 +674,7 @@ class dataprocessing:
 
         return combined_df
     
-    def pivot_table(self, df, index_col, columns, values_col, filters_dict=None, fill_value=0, aggfunc='sum', margins=False, margins_name="Total", datetime_trans_needed=True, reverse_header_order=False):
+    def pivot_table(self, df, index_col, columns, values_col, filters_dict=None, fill_value=0, aggfunc='sum', margins=False, margins_name="Total", datetime_trans_needed=True, reverse_header_order=False,fill_missing_weekly_dates=False,week_commencing='W-MON'):
         """
         Provides the ability to create pivot tables, filtering the data to get to data you want and then pivoting on certain columns
 
@@ -680,6 +690,8 @@ class dataprocessing:
             margins_name (str, optional): The name of the Totals columns. Defaults to "Total".
             datetime_trans_needed (bool, optional): Whether the index column needs to be transformed into datetime format. Defaults to False.
             reverse_header_order (bool, optional): Reverses the order of the column headers. Defaults to False.
+            fill_missing_weekly_dates (bool, optional): Fills in any weekly missing dates. Defaults to False.
+            week_commencing (str,optional): Fills in missing weeks if option is specified. Defaults to 'W-MON'.
 
         Returns:
             pandas.DataFrame: The pivot table specified
@@ -730,6 +742,10 @@ class dataprocessing:
         # Fill in any NaNs
         pivoted_df = pivoted_df.fillna(fill_value)
         
+        # If there is a need to fill in missing weeks
+        if fill_missing_weekly_dates == True:
+            pivoted_df = self.fill_weekly_date_range(pivoted_df, index_col, freq=week_commencing)
+
         return pivoted_df
 
     def apply_lookup_table_for_columns(self, df, col_names, to_find_dict, if_not_in_dict="Other", new_column_name="Mapping"):
@@ -1482,7 +1498,7 @@ class dataprocessing:
         df[new_col_name] = df[column_name].apply(categorize_text)
         return df
 
-    def compare_overlap(self, df1, df2, date_col):
+    def compare_overlap(df1, df2, date_col):
         """
         Compare overlapping periods between two DataFrames and provide a summary of total differences.
 
@@ -1509,21 +1525,23 @@ class dataprocessing:
         # Merge the dataframes on the date column to align data for comparison
         merged_df = pd.merge(df1_overlap, df2_overlap, on=date_col, suffixes=('_df1', '_df2'))
         
+        # Get the common columns between the two DataFrames, excluding the date column
+        common_cols = [col for col in df1.columns if col != date_col and col in df2.columns]
+        
         # Initialize a list to collect total differences for each column
         total_diff_list = []
         
-        # Compare the values in each column (excluding the date column)
+        # Create a DataFrame for the differences
         diff_df = pd.DataFrame({date_col: merged_df[date_col]})  # Initialize diff_df with the date column
         
-        for col in df1.columns:
-            if col != date_col:
-                # Calculate the difference for each row
-                diff_col = f'diff_{col}'
-                diff_df[diff_col] = merged_df[f'{col}_df1'] - merged_df[f'{col}_df2']
-                
-                # Calculate the total difference for the column and add it to the list
-                total_diff = diff_df[diff_col].sum()
-                total_diff_list.append({'Column': col, 'Total Difference': total_diff})
+        for col in common_cols:
+            # Calculate the difference for each row
+            diff_col = f'diff_{col}'
+            diff_df[diff_col] = merged_df[f'{col}_df1'] - merged_df[f'{col}_df2']
+            
+            # Calculate the total difference for the column and add it to the list
+            total_diff = diff_df[diff_col].sum()
+            total_diff_list.append({'Column': col, 'Total Difference': total_diff})
         
         # Create a DataFrame for the summary of total differences
         total_diff_df = pd.DataFrame(total_diff_list)
@@ -1535,6 +1553,162 @@ class dataprocessing:
         
         return diff_df, total_diff_df
     
+    # Convert week commencing col (should be most likely monday to sunday or vice versa)
+    def week_commencing_2_week_commencing_conversion(df,date_col,week_commencing='sun'):
+        """
+        Convert week commencing column in a DataFrame to the start of another day specified.
+
+        Args:
+            df (pandas.DataFrame): The DataFrame containing the date-based data.
+            date_col (str): The name of the date column in the DataFrame.
+            week_commencing (str, optional): The day of the week that the week starts on ('sun' for Sunday, 'mon' for Monday, etc.). Defaults to 'sun'.
+
+        Returns:
+            pandas.DataFrame: The original DataFrame with an additional column indicating the start of the week.
+        """
+        # Week commencing dictionary
+        day_dict = {"mon": 0, "tue": 1, "wed": 2, "thur": 3, "fri": 4, "sat": 5, "sun": 6}
+        df['week_start_'+ week_commencing] = df[date_col].apply(lambda x: x - pd.Timedelta(days=(x.weekday() - day_dict[week_commencing]) % 7))
+        
+        return df
+    
+    def plot_chart(df, date_col, value_cols, chart_type='line', title='Chart', x_title='Date', y_title='Values', **kwargs):
+        """
+        Plot various types of charts using Plotly.
+
+        Args:
+            df (pandas.DataFrame): DataFrame containing the data.
+            date_col (str): The name of the column with date information.
+            value_cols (list): List of columns to plot.
+            chart_type (str): Type of chart to plot ('line', 'bar', 'scatter', 'pie', 'box', 'heatmap', 'area', 'bubble', 'funnel', 'waterfall', 'contour', 'scatter3d').
+            title (str): Title of the chart.
+            x_title (str): Title of the x-axis.
+            y_title (str): Title of the y-axis.
+            **kwargs: Additional keyword arguments for customization.
+
+        Returns:
+            plotly.graph_objects.Figure: The Plotly figure object.
+        """
+        # Ensure the date column is in datetime format
+        df[date_col] = pd.to_datetime(df[date_col])
+        
+        # Initialize the figure
+        fig = go.Figure()
+        
+        # Make sure the date col is excluded from the line cols
+        value_cols = [x for x in value_cols if x!=date_col]
+
+        # Add each value column to the plot based on the chart type
+        for col in value_cols:
+            if chart_type == 'line':
+                fig.add_trace(go.Scatter(
+                    x=df[date_col],
+                    y=df[col],
+                    mode='lines',
+                    name=col,
+                    **kwargs
+                ))
+            elif chart_type == 'bar':
+                fig.add_trace(go.Bar(
+                    x=df[date_col],
+                    y=df[col],
+                    name=col,
+                    **kwargs
+                ))
+            elif chart_type == 'scatter':
+                fig.add_trace(go.Scatter(
+                    x=df[date_col],
+                    y=df[col],
+                    mode='markers',
+                    name=col,
+                    **kwargs
+                ))
+            elif chart_type == 'histogram':
+                fig.add_trace(go.Histogram(
+                    x=df[col],
+                    name=col,
+                    **kwargs
+                ))
+            elif chart_type == 'pie':
+                fig.add_trace(go.Pie(
+                    labels=df[date_col],  # or another column for labels
+                    values=df[col],
+                    name=col,
+                    **kwargs
+                ))
+            elif chart_type == 'box':
+                fig.add_trace(go.Box(
+                    y=df[col],
+                    name=col,
+                    **kwargs
+                ))
+            elif chart_type == 'heatmap':
+                fig.add_trace(go.Heatmap(
+                    z=df.pivot_table(index=date_col, columns=value_cols[0], values=value_cols[1]),
+                    x=df[value_cols[0]],
+                    y=df[date_col],
+                    **kwargs
+                ))
+            elif chart_type == 'area':
+                fig.add_trace(go.Scatter(
+                    x=df[date_col],
+                    y=df[col],
+                    mode='lines',  # Use 'lines+markers' if you want markers
+                    fill='tozeroy',  # Fill the area under the line
+                    name=col,
+                    **kwargs
+                ))
+            elif chart_type == 'bubble':
+                fig.add_trace(go.Scatter(
+                    x=df[value_cols[0]],
+                    y=df[value_cols[1]],
+                    mode='markers',
+                    marker=dict(size=df[value_cols[2]]),
+                    name='Bubble Chart',
+                    **kwargs
+                ))
+            elif chart_type == 'funnel':
+                fig.add_trace(go.Funnel(
+                    y=df[date_col],
+                    x=df[col],
+                    **kwargs
+                ))
+            elif chart_type == 'waterfall':
+                fig.add_trace(go.Waterfall(
+                    x=df[date_col],
+                    y=df[col],
+                    measure=df[value_cols[1]],  # measures like 'increase', 'decrease', 'total'
+                    **kwargs
+                ))
+            elif chart_type == 'contour':
+                fig.add_trace(go.Contour(
+                    z=df.pivot_table(index=value_cols[0], columns=value_cols[1], values=value_cols[2]),
+                    x=df[value_cols[0]],
+                    y=df[value_cols[1]],
+                    **kwargs
+                ))
+            elif chart_type == 'scatter3d':
+                fig.add_trace(go.Scatter3d(
+                    x=df[value_cols[0]],
+                    y=df[value_cols[1]],
+                    z=df[value_cols[2]],
+                    mode='markers',
+                    **kwargs
+                ))
+            else:
+                raise ValueError(f"Unsupported chart type: {chart_type}")
+
+        # Update the layout of the figure
+        fig.update_layout(
+            title=title,
+            xaxis_title=x_title,
+            yaxis_title=y_title,
+            legend_title='Series',
+            template='plotly_dark'
+        )
+        
+        return fig
+    
 ########################################################################################################################################
 ########################################################################################################################################
 

{imsciences-0.6.2.5.dist-info → imsciences-0.6.2.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: imsciences
-Version: 0.6.2.5
+Version: 0.6.2.7
 Summary: IMS Data Processing Package
 Author: IMS
 Author-email: cam@im-sciences.com

{imsciences-0.6.2.5.dist-info → imsciences-0.6.2.7.dist-info}/RECORD

@@ -3,14 +3,14 @@ dataprocessing/data-processing-functions.py,sha256=vE1vsZ8xOSbR9Bwlp9SWXwEHXQ0nF
 dataprocessing/datafunctions.py,sha256=vE1vsZ8xOSbR9Bwlp9SWXwEHXQ0nFydwGkvzHXf2f1Y,41
 imsciences/__init__.py,sha256=GIPbLmWc06sVcOySWwNvMNUr6XGOHqPLryFIWgtpHh8,78
 imsciences/datafunctions-IMS-24Ltp-3.py,sha256=3Snv-0iE_03StmyjtT-riOU9f4v8TaJWLoyZLJp6l8Y,141406
-imsciences/datafunctions.py,sha256=WOdezS0IW_n91eWr9SL_czLjCCkl5-951n58sjCG51Q,143447
+imsciences/datafunctions.py,sha256=PGuvgJIurXGWM8E1M_w9BijUJGBm5FTaZVE-C1_sPog,151382
 imsciences/datapull.py,sha256=TPY0LDgOkcKTBk8OekbD0Grg5x0SomAK2dZ7MuT6X1E,19000
 imsciencesdataprocessing/__init__.py,sha256=quSwsLs6IuLoA5Rzi0ZD40xZaQudwDteF7_ai9JfTPk,32
 imsciencesdataprocessing/datafunctions.py,sha256=vE1vsZ8xOSbR9Bwlp9SWXwEHXQ0nFydwGkvzHXf2f1Y,41
 imsdataprocessing/__init__.py,sha256=quSwsLs6IuLoA5Rzi0ZD40xZaQudwDteF7_ai9JfTPk,32
 imsdataprocessing/datafunctions.py,sha256=vE1vsZ8xOSbR9Bwlp9SWXwEHXQ0nFydwGkvzHXf2f1Y,41
-imsciences-0.6.2.5.dist-info/METADATA,sha256=HOqcQ7JFLITN-1vcra1XZTHQ72_JM_vajUfmpXNMyl4,854
-imsciences-0.6.2.5.dist-info/PKG-INFO-IMS-24Ltp-3,sha256=yqZbigwHjnYoqyI81PGz_AeofRFfOrwH_Vyawyef-mg,854
-imsciences-0.6.2.5.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-imsciences-0.6.2.5.dist-info/top_level.txt,sha256=hsENS-AlDVRh8tQJ6-426iUQlla9bPcGc0-UlFF0_iU,11
-imsciences-0.6.2.5.dist-info/RECORD,,
+imsciences-0.6.2.7.dist-info/METADATA,sha256=0IT7pWYxsHXerkqBVKsS2Zh1_6qwn1u7NL3mK44c4tk,854
+imsciences-0.6.2.7.dist-info/PKG-INFO-IMS-24Ltp-3,sha256=yqZbigwHjnYoqyI81PGz_AeofRFfOrwH_Vyawyef-mg,854
+imsciences-0.6.2.7.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+imsciences-0.6.2.7.dist-info/top_level.txt,sha256=hsENS-AlDVRh8tQJ6-426iUQlla9bPcGc0-UlFF0_iU,11
+imsciences-0.6.2.7.dist-info/RECORD,,