Update Examples in Docs (#724)

* make sure all examples are run in docs

* adjust panelview plot size

docs/difference-in-differences.qmd

@@ -119,7 +119,7 @@ pf.panelview(
     treat="treat",
     collapse_to_cohort=True,
     title = "Outcome Plot",
-    figsize=(1, 0.5),
+    figsize=(2, 0.75),
 )
 ```
 
@@ -142,7 +142,8 @@ pf.panelview(
     time="year",
     treat="treat",
     subsamp=100,
-    title = "Outcome Plot"
+    title = "Outcome Plot",
+    figsize=(2, 0.75),
 )
 ```
 

pyfixest/did/visualize.py

@@ -74,12 +74,13 @@ def panelview(
 
     Examples
     --------
-    ```python
+    ```{python}
     import pandas as pd
     import numpy as np
     import pyfixest as pf
 
-    df_het = pd.read_csv("pd.read_csv("pyfixest/did/data/df_het.csv")
+    url = "https://raw.githubusercontent.com/py-econometrics/pyfixest/master/pyfixest/did/data/df_het.csv"
+    df_het = pd.read_csv(url)
 
     # Inspect treatment assignment
     pf.panelview(

pyfixest/estimation/demean_.py

@@ -217,6 +217,39 @@ def demean(
     tuple[numpy.ndarray, bool]
         A tuple containing the demeaned array of shape (n_samples, n_features)
         and a boolean indicating whether the algorithm converged successfully.
+
+    Examples
+    --------
+    ```{python}
+    import numpy as np
+    import pyfixest as pf
+    from pyfixest.utils.dgps import get_blw
+    from pyfixest.estimation.demean_ import demean
+    from formulaic import model_matrix
+
+    fml = "y ~ treat | state + year"
+
+    data = get_blw()
+    data.head()
+
+    Y, rhs = model_matrix(fml, data)
+    X = rhs[0].drop(columns="Intercept")
+    fe = rhs[1].drop(columns="Intercept")
+    YX = np.concatenate([Y, X], axis=1)
+
+    # to numpy
+    Y = Y.to_numpy()
+    X = X.to_numpy()
+    YX = np.concatenate([Y, X], axis=1)
+    fe = fe.to_numpy().astype(int)  # demean requires fixed effects as ints!
+
+    YX_demeaned, success = demean(YX, fe, weights = np.ones(YX.shape[0]))
+    Y_demeaned = YX_demeaned[:, 0]
+    X_demeaned = YX_demeaned[:, 1:]
+
+    print(np.linalg.lstsq(X_demeaned, Y_demeaned, rcond=None)[0])
+    print(pf.feols(fml, data).coef())
+    ```
     """
     n_samples, n_features = x.shape
     n_factors = flist.shape[1]

pyfixest/estimation/feiv_.py

@@ -374,9 +374,7 @@ def IV_Diag(self, statistics: Optional[list[str]] = None):
             print("(Unadjusted) F stat :", F_stat_pf)
             print("Effective F stat :", F_stat_eff_pf)
 
-            # The example above generates the following results
-            # (Unadjusted) F stat : 52.81535560457482
-            # Effective F stat : 48.661542741328205
+            ```
         """
         # Set default statistics
         iv_diag_stat = ["f_stat", "effective_f"]

pyfixest/estimation/feols_.py

@@ -984,31 +984,25 @@ def wald_test(self, R=None, q=None, distribution="F"):
 
         Examples
         --------
+        ```{python}
         import numpy as np
         import pandas as pd
+        import pyfixest as pf
 
-        from pyfixest.estimation.estimation import feols
-
-        data = pd.read_csv("pyfixest/did/data/df_het.csv")
-        data = data.iloc[1:3000]
+        data = pf.get_data()
+        fit = pf.feols("Y ~ X1 + X2| f1", data, vcov={"CRV1": "f1"}, ssc=pf.ssc(adj=False))
 
         R = np.array([[1,-1]] )
         q = np.array([0.0])
 
-        fml = "dep_var ~ treat"
-        fit = feols(fml, data, vcov={"CRV1": "year"}, ssc=ssc(adj=False))
-
         # Wald test
         fit.wald_test(R=R, q=q, distribution = "chi2")
         f_stat = fit._f_statistic
         p_stat = fit._p_value
 
         print(f"Python f_stat: {f_stat}")
         print(f"Python p_stat: {p_stat}")
-
-        # The code above produces the following results :
-        # Python f_stat: 256.55432910297003
-        # Python p_stat: 9.67406627744023e-58
+        ```
         """
         _vcov = self._vcov
         _N = self._N
@@ -1332,15 +1326,15 @@ def ccv(
 
         Examples
         --------
-        ```python
-        from pyfixest.estimation import feols
-        from pyfixest.utils import get_data
+        ```{python}
+        import pyfixest as pf
+        import numpy as np
 
-        data = get_data()
-        data["D1"] = np.random.choice([0, 1], size=data.shape[0])
+        data = pf.get_data()
+        data["D"] = np.random.choice([0, 1], size=data.shape[0])
 
-        fit = feols("Y ~ D", data=data, vcov={"CRV1": "group_id"})
-        fit.ccv(treatment="D", pk=0.05, gk=0.5, n_splits=8, seed=123).head()
+        fit = pf.feols("Y ~ D", data=data, vcov={"CRV1": "group_id"})
+        fit.ccv(treatment="D", pk=0.05, qk=0.5, n_splits=8, seed=123).head()
         ```
         """
         assert (
@@ -1873,7 +1867,7 @@ def confint(
 
         Examples
         --------
-        ```python
+        ```{python}
         from pyfixest.utils import get_data
         from pyfixest.estimation import feols
 

pyfixest/estimation/model_matrix_fixest_.py

@@ -68,6 +68,20 @@ def model_matrix_fixest(
             List of variables interacted with i() syntax, None if not applicable.
         - 'X_is_empty' : bool
             Flag indicating whether X is empty.
+
+    Examples
+    --------
+    ```{python}
+    import pyfixest as pf
+    from pyfixest.estimation.model_matrix_fixest_ import model_matrix_fixest
+
+    data = pf.get_data()
+    fit = pf.feols("Y ~ X1 + f1 + f2", data=data)
+    FixestFormula = fit.FixestFormula
+
+    mm = model_matrix_fixest(FixestFormula, data)
+    mm
+    ```
     """
     FixestFormula.check_syntax()
 

pyfixest/estimation/multcomp.py

@@ -35,15 +35,14 @@ def bonferroni(models: ModelInputType, param: str) -> pd.DataFrame:
 
     Examples
     --------
-    ```python
-    from pyfixest.estimation import feols
+    ```{python}
+    import pyfixest as pf
     from pyfixest.utils import get_data
-    from pyfixest.multcomp import bonferroni
 
     data = get_data().dropna()
-    fit1 = feols("Y ~ X1", data=data)
-    fit2 = feols("Y ~ X1 + X2", data=data)
-    bonf_df = bonferroni([fit1, fit2], param="X1")
+    fit1 = pf.feols("Y ~ X1", data=data)
+    fit2 = pf.feols("Y ~ X1 + X2", data=data)
+    bonf_df = pf.bonferroni([fit1, fit2], param="X1")
     bonf_df
     ```
     """
@@ -106,18 +105,21 @@ def rwolf(
 
     Examples
     --------
-    ```python
-    from pyfixest.estimation import feols
+    ```{python}
+    import pyfixest as pf
     from pyfixest.utils import get_data
-    from pyfixest.multcomp import rwolf
 
     data = get_data().dropna()
-    fit = feols("Y ~ Y2 + X1 + X2", data=data)
-    rwolf(fit.to_list(), "X1", reps=9999, seed=123)
+    fit = pf.feols("Y ~ Y2 + X1 + X2", data=data)
+    pf.rwolf(fit, "X1", reps=9999, seed=123)
+
+    fit1 = pf.feols("Y ~ X1", data=data)
+    fit2 = pf.feols("Y ~ X1 + X2", data=data)
+    rwolf_df = pf.rwolf([fit1, fit2], "X1", reps=9999, seed=123)
+
+    # use randomization inference
+    rwolf_df = pf.rwolf([fit1, fit2], "X1", reps=9999, seed=123, sampling_method = "ri")
 
-    fit1 = feols("Y ~ X1", data=data)
-    fit2 = feols("Y ~ X1 + X2", data=data)
-    rwolf_df = rwolf([fit1, fit2], "X1", reps=9999, seed=123)
     rwolf_df
     ```
     """

pyfixest/report/summarize.py

@@ -122,6 +122,21 @@ def etable(
     pandas.DataFrame
         A styled DataFrame with the coefficients and standard errors of the models.
         When output is "tex", the LaTeX code is returned as a string.
+
+    Examples
+    --------
+    For more examples, take a look at the [regression tables and summary statistics vignette](https://py-econometrics.github.io/pyfixest/table-layout.html).
+
+    ```{python}
+    import pyfixest as pf
+
+    # load data
+    df = pf.get_data()
+    fit1 = pf.feols("Y~X1 + X2 | f1", df)
+    fit2 = pf.feols("Y~X1 + X2 | f1 + f2", df)
+
+    pf.etable([fit1, fit2])
+    ```
     """
     if signif_code is None:
         signif_code = [0.001, 0.01, 0.05]
@@ -1189,6 +1204,18 @@ def dtable(
     Returns
     -------
     A table in the specified format.
+
+    Examples
+    --------
+    For more examples, take a look at the [regression tables and summary statistics vignette](https://py-econometrics.github.io/pyfixest/table-layout.html).
+
+    ```{python}
+    import pyfixest as pf
+
+    # load data
+    df = pf.get_data()
+    pf.dtable(df, vars = ["Y", "X1", "X2", "f1"])
+    ```
     """
     if stats is None:
         stats = ["count", "mean", "std"]