DOC: Correct typos in Polynomial Regression notebook (#940)

* DOC: Correct a typo: an 1d -> a 1d

* DOC: Correct typos in Polynomial Regression notebook

Author: star1327p

bambi/transformations.py

@@ -95,7 +95,7 @@ def truncated(x, lb=None, ub=None):
     if lb is None and ub is None:
         raise ValueError("'lb' and 'ub' cannot both be None")
 
-    # Process lower bound so we get an 1d array with the adequate values
+    # Process lower bound so we get a 1d array with the adequate values
     if lb is not None:
         lower = np.asarray(lb)
         if lower.ndim == 0:
@@ -107,7 +107,7 @@ def truncated(x, lb=None, ub=None):
     else:
         lower = np.full(len(x), -np.inf)
 
-    # Process upper bound so we get an 1d array with the adequate values
+    # Process upper bound so we get a 1d array with the adequate values
     if ub is not None:
         upper = np.asarray(ub)
         if upper.ndim == 0:

docs/notebooks/polynomial_regression.ipynb

@@ -38,7 +38,7 @@
     "\n",
     "$$x_f = \\frac{1}{2} a t^2 + v_0 t + x_0$$\n",
     "\n",
-    "Where $x_0$ and $x_f$ are the initial and final locations, $v_0$ is the initial velocity, and $a$ is acceleration.\n",
+    "where $x_0$ and $x_f$ are the initial and final locations, $v_0$ is the initial velocity, and $a$ is acceleration.\n",
     "\n",
     "## A falling ball\n",
     "\n",
@@ -87,7 +87,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Casting the equation $x_f = \\frac{1}{2} g t^2 + x_0$ into a regression context, we let time ($t$) be the independent variable, and final location ($x_f$) be the response/dependent variable. This allows our coefficients to be proportional to $g$ and $x_0$. The intercept, $\\beta_0$ corresponds exactly to $x_0$. Letting $\\beta_1 = \\frac{1}{2} g$ then gives $g = 2\\beta_1$ when $x_1 = t^2$, meaning we\"re doing _polynomial regression_. We can put this into Bambi via the following, optionally including the `+ 1` to emphasize that we choose to include the coefficient. "
+    "Casting the equation $x_f = \\frac{1}{2} g t^2 + x_0$ into a regression context, we let time ($t$) be the independent variable, and final location ($x_f$) be the response/dependent variable. This allows our coefficients to be proportional to $g$ and $x_0$. The intercept, $\\beta_0$ corresponds exactly to $x_0$. Letting $\\beta_1 = \\frac{1}{2} g$ then gives $g = 2\\beta_1$ when $x_1 = t^2$, meaning we're doing _polynomial regression_. We can put this into Bambi via the following, optionally including the `+ 1` to emphasize that we choose to include the coefficient. "
    ]
   },
   {
@@ -145,13 +145,13 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The term `I(t**2)` indicates to evaluate inside the `I`. For including _just the $t^2$ term_, you can express it any of the following ways:  \n",
+    "The term `I(t**2)` indicates to evaluate inside the `I`. For including _just the $t^2$ term_, you can express it in any of the following ways:  \n",
     "\n",
     "- `I(t**2)`\n",
     "- `{t**2}`\n",
     "- Square the data directly, and pass it as a new column\n",
     "\n",
-    "To verify, we\"ll fit the other two versions as well."
+    "To verify, we'll fit the other two versions as well."
    ]
   },
   {
@@ -487,7 +487,7 @@
     "\n",
     "$$x_f = \\beta_0 + \\beta_1 t + \\beta_2 t^2$$\n",
     "\n",
-    "Which then maps the solved coefficents to the following: $\\beta_0 = x_0$, $\\beta_1 = v_0$, and $\\beta_2 = \\frac{g}{2}$."
+    "which then maps the solved coefficents to the following: $\\beta_0 = x_0$, $\\beta_1 = v_0$, and $\\beta_2 = \\frac{g}{2}$."
    ]
   },
   {