diffindiff 2.3.4__tar.gz → 2.3.5__tar.gz

{diffindiff-2.3.4 → diffindiff-2.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: diffindiff
-Version: 2.3.4
+Version: 2.3.5
 Summary: diffindiff: Python library for convenient Difference-in-Differences analyses
 Author: Thomas Wieland
 Author-email: geowieland@googlemail.com
@@ -27,7 +27,7 @@ Thomas Wieland [ORCID](https://orcid.org/0000-0001-5168-9846) [EMail](mailto:geo
 
 If you use this software, please cite:
 
-Wieland, T. (2026). diffindiff: A Python library for convenient difference-in-differences analyses (Version 2.3.4) [Computer software]. Zenodo. https://doi.org/10.5281/zenodo.18656820
+Wieland, T. (2026). diffindiff: A Python library for convenient difference-in-differences analyses (Version 2.3.5) [Computer software]. Zenodo. https://doi.org/10.5281/zenodo.18656820
 
 
 ## Installation
@@ -173,7 +173,10 @@ See the /tests directory for usage examples of most of the included functions.
 This software was developed without the use of AI-generated code. The Continue Agent in Microsoft Visual Studio Code using the GPT-5 mini model (by OpenAI) was used solely to assist in drafting and refining docstrings for documentation. The corresponding guidelines and constraints defined by the author are documented in `AGENTS-docstrings.md` in the [public GitHub repository](https://github.com/geowieland/diffindiff_official).
 
 
-## What's new (v2.3.4)
+## What's new (v2.3.5)
 
 - Bugfixes:
-  - Fixed bug in DiffData instance creation in diddata.merge_data()
+  - Test whether input data is panel data via didtools.is_panel() which is included in didanalysis_helper.data_diagnostics()
+  - Fixed false test results given continuous treatments are accepted in didtools.is_simultaneous()
+  - Fixed false test results given continuous treatments are accepted in didtools.is_prepost()
+  - Argument 'pre_post' is passed to is_simultaneous() in didanalysis_helper.treatment_diagnostics()

{diffindiff-2.3.4 → diffindiff-2.3.5}/README.md

@@ -19,7 +19,7 @@ Thomas Wieland [ORCID](https://orcid.org/0000-0001-5168-9846) [EMail](mailto:geo
 
 If you use this software, please cite:
 
-Wieland, T. (2026). diffindiff: A Python library for convenient difference-in-differences analyses (Version 2.3.4) [Computer software]. Zenodo. https://doi.org/10.5281/zenodo.18656820
+Wieland, T. (2026). diffindiff: A Python library for convenient difference-in-differences analyses (Version 2.3.5) [Computer software]. Zenodo. https://doi.org/10.5281/zenodo.18656820
 
 
 ## Installation
@@ -165,7 +165,10 @@ See the /tests directory for usage examples of most of the included functions.
 This software was developed without the use of AI-generated code. The Continue Agent in Microsoft Visual Studio Code using the GPT-5 mini model (by OpenAI) was used solely to assist in drafting and refining docstrings for documentation. The corresponding guidelines and constraints defined by the author are documented in `AGENTS-docstrings.md` in the [public GitHub repository](https://github.com/geowieland/diffindiff_official).
 
 
-## What's new (v2.3.4)
+## What's new (v2.3.5)
 
 - Bugfixes:
-  - Fixed bug in DiffData instance creation in diddata.merge_data()
+  - Test whether input data is panel data via didtools.is_panel() which is included in didanalysis_helper.data_diagnostics()
+  - Fixed false test results given continuous treatments are accepted in didtools.is_simultaneous()
+  - Fixed false test results given continuous treatments are accepted in didtools.is_prepost()
+  - Argument 'pre_post' is passed to is_simultaneous() in didanalysis_helper.treatment_diagnostics()

{diffindiff-2.3.4 → diffindiff-2.3.5}/diffindiff/config.py

@@ -4,15 +4,15 @@
 # Author:      Thomas Wieland 
 #              ORCID: 0000-0001-5168-9846
 #              mail: geowieland@googlemail.com              
-# Version:     1.0.12
-# Last update: 2026-03-14 11:28
+# Version:     1.0.13
+# Last update: 2026-03-16 17:54
 # Copyright (c) 2025-2026 Thomas Wieland
 #-----------------------------------------------------------------------
 
 # Basic config:
 
 PACKAGE_NAME = "diffindiff"
-PACKAGE_VERSION = "2.3.4"
+PACKAGE_VERSION = "2.3.5"
 
 VERBOSE = False
 

{diffindiff-2.3.4 → diffindiff-2.3.5}/diffindiff/didanalysis.py

@@ -4,8 +4,8 @@
 # Author:      Thomas Wieland 
 #              ORCID: 0000-0001-5168-9846
 #              mail: geowieland@googlemail.com              
-# Version:     2.3.3
-# Last update: 2026-03-12 19:40
+# Version:     2.3.4
+# Last update: 2026-03-16 17:39
 # Copyright (c) 2024-2026 Thomas Wieland
 #-----------------------------------------------------------------------
 
@@ -1290,7 +1290,7 @@ class DiffModel:
         
         TG_col_ = f"{config.TG_COL}{config.DELIMITER}{treatment}"
         TT_col_ = f"{config.TT_COL}{config.DELIMITER}{treatment}"
-        TGxTT_ = f"Placebo{config.DELIMITER}{treatment}"
+        TGxTT_ = f"Placebo{config.DELIMITER}{treatment}"        
         
         if TG_col is None and TG_col_ not in model_config["TG_col"]:
             raise ValueError(f"No treatment group identification variable for treatment {treatment}. Please state TG_col = your_treatment_group_dummy.")
@@ -2199,6 +2199,29 @@ def did_analysis(
     ...     intercept=False
     ...     )
     >>> Hesse_model1.summary()
+    >>> Hesse_model5=did_analysis(
+    ...     data=Corona_Hesse,
+    ...     unit_col="REG_NAME",
+    ...     time_col="infection_date",
+    ...     treatment_col=["Nighttime_curfew", "Mobility_restrictions", "Retail_closed", "CR_private_2"],
+    ...     covariates=["infections_cum", "R7_rm_lag10"],   
+    ...     outcome_col="R7_rm"
+    ... )
+    >>> Hesse_model5.summary()
+    >>> Hesse_model6=did_analysis(
+    ...     data=Corona_Hesse,
+    ...     unit_col="REG_NAME",
+    ...     time_col="infection_date",
+    ...     treatment_col=["Nighttime_curfew", "Mobility_restrictions"],
+    ...     covariates=["infections_cum", "R7_rm_lag10"],
+    ...     interactions={
+    ...         0: {
+    ...            "name": "curfew_and_mobility",
+    ...            "treatments": ["Nighttime_curfew", "Nighttime_curfew"]
+    ...           }        
+    ...     },
+    ...     outcome_col="R7_rm"
+    ... )
     """
 
     if TG_col is None:
@@ -2274,7 +2297,7 @@ def did_analysis(
         verbose=verbose
     )
     treatment_diagnostics = treatment_diagnostics_results[0]
-    staggered_adoption = treatment_diagnostics_results[1]
+    staggered_adoption = treatment_diagnostics_results[1]    
     
     if no_treatments > 1:        
         
@@ -2445,6 +2468,10 @@ def did_analysis(
         
         pre_post = True
         
+        FE_unit = False
+        FE_time = False
+        FE_group = False
+        
     if log_outcome:
         
         if missing_replace_by_zero:

{diffindiff-2.3.4 → diffindiff-2.3.5}/diffindiff/didanalysis_helper.py

@@ -4,8 +4,8 @@
 # Author:      Thomas Wieland 
 #              ORCID: 0000-0001-5168-9846
 #              mail: geowieland@googlemail.com              
-# Version:     1.1.1
-# Last update: 2025-03-12 20:44
+# Version:     1.1.2
+# Last update: 2025-03-16 17:46
 # Copyright (c) 2025-2026 Thomas Wieland
 #-----------------------------------------------------------------------
 
@@ -531,6 +531,16 @@ def data_diagnostics(
     if cols_relevant is None:
         cols_relevant = []
 
+    modeldata_ispanel = tools.is_panel(
+        data=data,
+        unit_col=unit_col,
+        time_col=time_col,
+        verbose=verbose
+    )
+    
+    if not modeldata_ispanel[0]:
+        raise TypeError(f"A difference-in-differences analysis requires panel data with at least two observational units and time points, respectively. Input data is likely {modeldata_ispanel[1]}")
+
     modeldata_ismissing = tools.is_missing(
         data, 
         drop_missing = drop_missing,
@@ -560,7 +570,8 @@ def data_diagnostics(
     modeldata_isprepost = tools.is_prepost(
         data = data,
         unit_col = unit_col,
-        time_col = time_col
+        time_col = time_col,
+        verbose = verbose
         )
     if modeldata_isprepost:
         data_type = config.PREPOST_PANELDATA_DESCRIPTION
@@ -666,6 +677,7 @@ def treatment_diagnostics(
             unit_col = unit_col,
             time_col = time_col,
             treatment_col = treatment,
+            pre_post = pre_post,
             verbose = verbose
             )
         if is_simultaneous_result:

{diffindiff-2.3.4 → diffindiff-2.3.5}/diffindiff/didtools.py

@@ -4,8 +4,8 @@
 # Author:      Thomas Wieland 
 #              ORCID: 0000-0001-5168-9846
 #              mail: geowieland@googlemail.com              
-# Version:     2.2.1
-# Last update: 2026-03-03 17:34
+# Version:     2.2.2
+# Last update: 2026-03-16 18:04
 # Copyright (c) 2025-2026 Thomas Wieland
 #-----------------------------------------------------------------------
 
@@ -498,11 +498,11 @@ def is_simultaneous(
     --------
     >>> is_simultaneous(df, 'unit', 'time', 'treat')
     """
-
+    
     if pre_post:
         
         if verbose:
-            print(f"Checking whether treatment '{treatment_col}' is simultaneous or staggered", end = " ... ")
+            print(f"Data for treatment '{treatment_col}' is pre-post data and considered as simultaneous.")
         
         simultaneous = True
     
@@ -521,25 +521,24 @@ def is_simultaneous(
         treatment_group = data_isnotreatment[1]
         data_TG = data[data[unit_col].isin(treatment_group)]
 
-        data_TG_pivot = data_TG.pivot_table(
-            index = time_col,
-            columns = unit_col, 
-            values = treatment_col
-            )
+        treated = data_TG[treatment_col] > 0
 
-        if config.ACCEPT_CONTINUOUS_TREATMENTS:
-            simultaneous = (data_TG_pivot.nunique(axis=1) > 0).all()
-        else:
-            simultaneous = (data_TG_pivot.nunique(axis=1) == 1).all()
+        simultaneous = (
+            data_TG.assign(treated=treated)
+            .groupby(time_col)["treated"]
+            .nunique()
+            .le(1)
+            .all()
+        )
 
-    if verbose:
-        print("OK")
+        if verbose:
+            print("OK")
 
         if not simultaneous and data_isnotreatment[0]:
             print(f"NOTE: treatment '{treatment_col}' is not simultaneous.")
 
-    if simultaneous and not data_isnotreatment[0]:
-        print(f"WARNING: treatment '{treatment_col}' is simultaneous and does not include a {config.NO_TREATMENT_CG_DESCRIPTION}")
+        if simultaneous and not data_isnotreatment[0]:
+            print(f"WARNING: treatment '{treatment_col}' is simultaneous and does not include a {config.NO_TREATMENT_CG_DESCRIPTION}")
 
     return simultaneous
 
@@ -905,6 +904,65 @@ def is_parallel(
         test_ols_model
         ]
 
+def is_panel(
+    data: pd.DataFrame,
+    unit_col: str,
+    time_col: str,
+    verbose: bool = config.VERBOSE
+    ):
+
+    """
+    Check whether panel data is panel data 
+    (>=2 units and >= 2 timepoints).
+
+    Parameters
+    ----------
+    data : pandas.DataFrame
+        Panel data.
+    unit_col : str
+        Column name for units.
+    time_col : str
+        Column name for time.
+    verbose : bool, optional
+        If True, print progress messages.
+
+    Returns
+    -------
+    bool
+        True if panel data, False otherwise.
+
+    Examples
+    --------
+    >>> is_panel(df, 'unit', 'time')
+    """
+    
+    if verbose:
+        print("Checking whether input data is panel data", end = " ... ")
+    
+    panel = True
+    other_data_type = ""
+    
+    no_units = data[unit_col].nunique()
+    no_timepoints = data[time_col].nunique()
+    
+    if no_units < 2 or no_timepoints < 2:
+        panel = False
+        
+    if verbose:
+        print("OK")
+        
+    if no_units < 2 and no_timepoints >= 2:
+        other_data_type = "Single time series data"
+    elif no_units > 2 and no_timepoints < 2:
+        other_data_type = "Cross-sectional data"
+    elif no_units < 2 and no_timepoints < 2:
+        other_data_type = "Single observation"
+        
+    if not panel:
+        print(f"WARNING: Input data contains {no_units} units and {no_timepoints} time points. It is not panel data but likely: {other_data_type}.")
+        
+    return panel, other_data_type
+
 def is_prepost(
     data: pd.DataFrame,
     unit_col: str,
@@ -937,9 +995,12 @@ def is_prepost(
     """
 
     if verbose:
-        print("Checking whether panel data is pre-post or multi-period", end = " ... ")
+        print("Checking whether panel data is pre-post or multi-period", end = " ... ")    
+    
+    prepost = False
     
-    prepost = (data.groupby(unit_col)[time_col].nunique().le(2).all())
+    if data[time_col].nunique() == 2:
+        prepost = True        
     
     if verbose:
         print("OK")

{diffindiff-2.3.4 → diffindiff-2.3.5}/diffindiff/tests/tests_diffindiff.py

@@ -4,8 +4,8 @@
 # Author:      Thomas Wieland 
 #              ORCID: 0000-0001-5168-9846
 #              mail: geowieland@googlemail.com              
-# Version:     2.0.12
-# Last update: 2026-03-01 11:29
+# Version:     2.0.14
+# Last update: 2026-03-16 17:35
 # Copyright (c) 2025-2026 Thomas Wieland
 #-----------------------------------------------------------------------
 
@@ -82,7 +82,7 @@ curfew_data_prepost=create_data(
 curfew_data_prepost.summary()
 # Summary of created data
 
-curfew_model_prepost=curfew_data_prepost.analysis()
+curfew_model_prepost=curfew_data_prepost.analysis(verbose=True)
 # Model analysis of created data
 
 print(curfew_model_prepost.treatment_effects())
@@ -184,7 +184,7 @@ curfew_data=create_data(
 curfew_data.summary()
 # Summary of created treatment data
 
-curfew_model=curfew_data.analysis()
+curfew_model=curfew_data.analysis(verbose=True)
 # Model analysis of created data
 
 curfew_model.summary()
@@ -211,6 +211,7 @@ curfew_placebo = curfew_model.placebo(
 curfew_placebo.summary()
 # Summary of placebo test
 
+
 # Two-way-fixed-effects model:
 
 curfew_model_FE=curfew_data.analysis(
@@ -340,7 +341,8 @@ Hesse_model1=did_analysis(
     time_col="infection_date",
     treatment_col="Nighttime_curfew",    
     outcome_col="R7_rm",
-    intercept=False
+    intercept=False,
+    verbose=True
     )
 # Model with staggered adoption (FE automatically)
 
@@ -430,8 +432,28 @@ Hesse_model5=did_analysis(
     time_col="infection_date",
     treatment_col=["Nighttime_curfew", "Mobility_restrictions", "Retail_closed", "CR_private_2"],
     covariates=["infections_cum", "R7_rm_lag10"],   
-    outcome_col="R7_rm")
+    outcome_col="R7_rm"
+    )
 # Model with four interventions (two staggered, two without control conditions)
 
 Hesse_model5.summary()
+# Model summary
+
+Hesse_model6=did_analysis(
+    data=Corona_Hesse,
+    unit_col="REG_NAME",
+    time_col="infection_date",
+    treatment_col=["Nighttime_curfew", "School_holidays"],
+    covariates=["infections_cum", "R7_rm_lag10"],
+    interactions={
+        0: {
+           "name": "curfew_and_holidays",
+           "treatments": ["Nighttime_curfew", "School_holidays"]
+           }        
+    },
+    outcome_col="R7_rm"
+    )
+# Model with two interventions and one interaction of the two treatments
+
+Hesse_model6.summary()
 # Model summary

{diffindiff-2.3.4 → diffindiff-2.3.5}/diffindiff.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: diffindiff
-Version: 2.3.4
+Version: 2.3.5
 Summary: diffindiff: Python library for convenient Difference-in-Differences analyses
 Author: Thomas Wieland
 Author-email: geowieland@googlemail.com
@@ -27,7 +27,7 @@ Thomas Wieland [ORCID](https://orcid.org/0000-0001-5168-9846) [EMail](mailto:geo
 
 If you use this software, please cite:
 
-Wieland, T. (2026). diffindiff: A Python library for convenient difference-in-differences analyses (Version 2.3.4) [Computer software]. Zenodo. https://doi.org/10.5281/zenodo.18656820
+Wieland, T. (2026). diffindiff: A Python library for convenient difference-in-differences analyses (Version 2.3.5) [Computer software]. Zenodo. https://doi.org/10.5281/zenodo.18656820
 
 
 ## Installation
@@ -173,7 +173,10 @@ See the /tests directory for usage examples of most of the included functions.
 This software was developed without the use of AI-generated code. The Continue Agent in Microsoft Visual Studio Code using the GPT-5 mini model (by OpenAI) was used solely to assist in drafting and refining docstrings for documentation. The corresponding guidelines and constraints defined by the author are documented in `AGENTS-docstrings.md` in the [public GitHub repository](https://github.com/geowieland/diffindiff_official).
 
 
-## What's new (v2.3.4)
+## What's new (v2.3.5)
 
 - Bugfixes:
-  - Fixed bug in DiffData instance creation in diddata.merge_data()
+  - Test whether input data is panel data via didtools.is_panel() which is included in didanalysis_helper.data_diagnostics()
+  - Fixed false test results given continuous treatments are accepted in didtools.is_simultaneous()
+  - Fixed false test results given continuous treatments are accepted in didtools.is_prepost()
+  - Argument 'pre_post' is passed to is_simultaneous() in didanalysis_helper.treatment_diagnostics()

{diffindiff-2.3.4 → diffindiff-2.3.5}/setup.py

@@ -7,7 +7,7 @@ def read_README():
     
 setup(
     name='diffindiff',
-    version='2.3.4',
+    version='2.3.5',
     description='diffindiff: Python library for convenient Difference-in-Differences analyses',
     packages=find_packages(include=["diffindiff", "diffindiff.tests"]),
     include_package_data=True,

diffindiff-2.3.4/diffindiff/__init__.py

@@ -1,4 +0,0 @@
-from diffindiff.didanalysis import DiffModel, did_analysis
-from diffindiff.diddata import DiffGroups, create_groups, DiffTreatment, create_treatment, DiffData, merge_data, create_data
-from diffindiff.didtools import is_balanced, is_missing, is_simultaneous, is_notreatment, date_counter, check_columns, is_binary, is_parallel, unique, model_wrapper, treatment_times, clean_column_name
-from diffindiff.didanalysis_helper import create_fixed_effects, create_specific_time_trends, create_specific_treatment_effects, create_spillover