diff --git a/bofire/data_models/objectives/api.py b/bofire/data_models/objectives/api.py
index c278e17c..53ccb5a9 100644
--- a/bofire/data_models/objectives/api.py
+++ b/bofire/data_models/objectives/api.py
@@ -1,6 +1,12 @@
 from typing import Union
 
 from bofire.data_models.objectives.categorical import ConstrainedCategoricalObjective
+from bofire.data_models.objectives.desirabilities import (
+    DecreasingDesirabilityObjective,
+    DesirabilityObjective,
+    IncreasingDesirabilityObjective,
+    PeakDesirabilityObjective,
+)
 from bofire.data_models.objectives.identity import (
     IdentityObjective,
     MaximizeObjective,
@@ -25,6 +31,7 @@
     IdentityObjective,
     SigmoidObjective,
     ConstrainedObjective,
+    DesirabilityObjective,
 ]
 
 AnyCategoricalObjective = ConstrainedCategoricalObjective
@@ -36,7 +43,15 @@
     TargetObjective,
 ]
 
-AnyRealObjective = Union[MaximizeObjective, MinimizeObjective, CloseToTargetObjective]
+AnyRealObjective = Union[
+    MaximizeObjective,
+    MinimizeObjective,
+    CloseToTargetObjective,
+    DesirabilityObjective,
+    IncreasingDesirabilityObjective,
+    DecreasingDesirabilityObjective,
+    PeakDesirabilityObjective,
+]
 
 AnyObjective = Union[
     MaximizeObjective,
@@ -47,4 +62,8 @@
     CloseToTargetObjective,
     ConstrainedCategoricalObjective,
     MovingMaximizeSigmoidObjective,
+    DesirabilityObjective,
+    IncreasingDesirabilityObjective,
+    DecreasingDesirabilityObjective,
+    PeakDesirabilityObjective,
 ]
diff --git a/bofire/data_models/objectives/desirabilities.py b/bofire/data_models/objectives/desirabilities.py
new file mode 100644
index 00000000..229e9f02
--- /dev/null
+++ b/bofire/data_models/objectives/desirabilities.py
@@ -0,0 +1,221 @@
+from abc import abstractmethod
+from typing import Literal, Optional, Union
+
+import numpy as np
+import pandas as pd
+import pydantic
+
+from bofire.data_models.objectives.identity import IdentityObjective
+
+
+class DesirabilityObjective(IdentityObjective):
+    """Abstract class for desirability objectives. Works as Identity Objective"""
+
+    type: Literal["DesirabilityObjective"] = "DesirabilityObjective"  # type: ignore
+    clip: bool = True
+
+    @pydantic.model_validator(mode="after")
+    def validate_clip(self):
+        if self.clip:
+            return self
+
+        log_shapes = {
+            key: val
+            for (key, val) in self.__dict__.items()
+            if key.startswith("log_shape_factor")
+        }
+        for key, log_shape_ in log_shapes.items():
+            if log_shape_ != 0:
+                raise ValueError(
+                    f"Log shape factor {key} must be zero if clip is False."
+                )
+        return self
+
+    def __call__(
+        self, x: Union[pd.Series, np.ndarray], x_adapt
+    ) -> Union[pd.Series, np.ndarray]:
+        """Wrapper function for to call numpy and torch functions with series or numpy arrays. matches __call__
+        signature of objectives."""
+
+        convert_to_series = False
+        if isinstance(x, pd.Series):
+            convert_to_series = True
+            name = x.name
+            x = x.values
+
+        y = self.call_numpy(x)
+
+        if convert_to_series:
+            return pd.Series(y, name=name)
+
+        return y
+
+    @abstractmethod
+    def call_numpy(self, x: np.ndarray) -> np.ndarray:
+        raise NotImplementedError()
+
+
+class IncreasingDesirabilityObjective(DesirabilityObjective):
+    """An objective returning a reward the scaled identity, but trimmed at the bounds:
+
+        d = ((x - lower_bound) / (upper_bound - lower_bound))^t
+
+    if clip is True, the reward is zero for x < lower_bound and one for x > upper_bound.
+
+    where:
+
+        t = exp(log_shape_factor)
+
+    Note, that with clipping the reward is always between zero and one.
+
+    Attributes:
+        clip (bool): Whether to clip the values below/above the lower/upper bound, by
+            default True.
+        log_shape_factor (float): Logarithm of the shape factor:
+            Whether the interpolation between the lower bound and the upper is linear (=0),
+            convex (>0) or concave (<0) , by default 0.0.
+        w (float): relative weight, by default = 1.
+        bounds (tuple[float]): lower and upper bound of the desirability. Below
+            bounds[0] the desirability is =0 (if clip=True) or <0 (if clip=False). Above
+            bounds[1] the desirability is =1  (if clip=True) or >1 (if clip=False).
+            Defaults to (0, 1).
+    """
+
+    type: Literal["IncreasingDesirabilityObjective"] = "IncreasingDesirabilityObjective"  # type: ignore
+    log_shape_factor: float = 0.0
+
+    def call_numpy(
+        self,
+        x: np.ndarray,
+        x_adapt: Optional[Union[pd.Series, np.ndarray]] = None,
+    ) -> np.ndarray:
+        y = np.zeros(x.shape)
+        if self.clip:
+            y[x < self.lower_bound] = 0.0
+            y[x > self.upper_bound] = 1.0
+            between = (x >= self.lower_bound) & (x <= self.upper_bound)
+        else:
+            between = np.full(x.shape, True)
+
+        t = np.exp(self.log_shape_factor)
+
+        y[between] = np.power(
+            (x[between] - self.lower_bound) / (self.upper_bound - self.lower_bound), t
+        )
+
+        return y
+
+
+class DecreasingDesirabilityObjective(DesirabilityObjective):
+    """An objective returning a reward the negative, shifted scaled identity, but trimmed at the bounds:
+
+        d = ((upper_bound - x) / (upper_bound - lower_bound))^t
+
+    where:
+
+        t = exp(log_shape_factor)
+
+    Note, that with clipping the reward is always between zero and one.
+
+    Attributes:
+        clip (bool): Whether to clip the values below/above the lower/upper bound, by
+            default True.
+        log_shape_factor (float): Logarithm of the shape factor:
+            Whether the interpolation between the lower bound and the upper is linear (=0),
+            convex (>0) or concave (<0) , by default 0.0.
+        w (float): relative weight, by default = 1.
+        bounds (tuple[float]): lower and upper bound of the desirability. Below
+            bounds[0] the desirability is =1 (if clip=True) or >1 (if clip=False). Above
+            bounds[1] the desirability is =0  (if clip=True) or <0 (if clip=False).
+            Defaults to (0, 1).
+    """
+
+    type: Literal["DecreasingDesirabilityObjective"] = "DecreasingDesirabilityObjective"  # type: ignore
+    log_shape_factor: float = 0.0
+
+    def call_numpy(
+        self,
+        x: np.ndarray,
+        x_adapt: Optional[Union[pd.Series, np.ndarray]] = None,
+    ) -> np.ndarray:
+        y = np.zeros(x.shape)
+        if self.clip:
+            y[x < self.lower_bound] = 1.0
+            y[x > self.upper_bound] = 0.0
+            between = (x >= self.lower_bound) & (x <= self.upper_bound)
+        else:
+            between = np.full(x.shape, True)
+
+        t = np.exp(self.log_shape_factor)
+
+        y[between] = np.power(
+            (self.upper_bound - x[between]) / (self.upper_bound - self.lower_bound), t
+        )
+
+        return y
+
+
+class PeakDesirabilityObjective(DesirabilityObjective):
+    """
+    A piecewise (linear or convex/concave) objective that increases from the lower bound
+    to the peak position and decreases from the peak position to the upper bound.
+
+    Attributes:
+        clip (bool): Whether to clip the values below/above the lower/upper bound, by
+            default True.
+        log_shape_factor (float): Logarithm of the shape factor for the increasing part:
+            Whether the interpolation between the lower bound and the peak is linear (=0),
+            convex (>1) or concave (<1) , by default 0.0.
+        log_shape_factor_decreasing (float): Logarithm of the shape factor for the
+            decreasing part. Whether the interpolation between the peak and the upper
+            bound is linear (=0), convex (>0) or concave (<0), by default 0.0.
+        peak_position (float): Position of the peak, by default 0.5.
+        w (float): relative weight: desirability, when x=peak_position, by default = 1.
+        bounds (tuple[float]): lower and upper bound of the desirability. Below
+            bounds[0] the desirability is =0 (if clip=True) or <0 (if clip=False). Above
+            bounds[1] the desirability is =0  (if clip=True) or <0 (if clip=False).
+            Defaults to (0, 1).
+    """
+
+    type: Literal["PeakDesirabilityObjective"] = "PeakDesirabilityObjective"  # type: ignore
+    log_shape_factor: float = 0.0
+    log_shape_factor_decreasing: float = 0.0  # often named log_t
+    peak_position: float = 0.5  # often named T
+
+    def call_numpy(
+        self,
+        x: np.ndarray,
+        x_adapt: Optional[Union[pd.Series, np.ndarray]] = None,
+    ) -> np.ndarray:
+        y = np.zeros(x.shape)
+        if self.clip:
+            Incr = (x >= self.lower_bound) & (x <= self.peak_position)
+            Decr = (x <= self.upper_bound) & (x > self.peak_position)
+        else:
+            Incr, Decr = x <= self.peak_position, x > self.peak_position
+
+        s: float = np.exp(self.log_shape_factor)
+        t: float = np.exp(self.log_shape_factor_decreasing)
+        y[Incr] = np.power(
+            np.divide(
+                (x[Incr] - self.lower_bound), (self.peak_position - self.lower_bound)
+            ),
+            s,
+        )
+        y[Decr] = np.power(
+            np.divide(
+                (x[Decr] - self.upper_bound), (self.peak_position - self.upper_bound)
+            ),
+            t,
+        )
+
+        return y * self.w
+
+    @pydantic.model_validator(mode="after")
+    def validate_peak_position(self):
+        bounds = self.bounds
+        if self.peak_position < bounds[0] or self.peak_position > bounds[1]:
+            raise ValueError(
+                f"Peak position must be within bounds {bounds}, got {self.peak_position}"
+            )
+        return self
diff --git a/bofire/utils/torch_tools.py b/bofire/utils/torch_tools.py
index 101cd6aa..88976ae8 100644
--- a/bofire/utils/torch_tools.py
+++ b/bofire/utils/torch_tools.py
@@ -21,12 +21,15 @@
     CloseToTargetObjective,
     ConstrainedCategoricalObjective,
     ConstrainedObjective,
+    DecreasingDesirabilityObjective,
+    IncreasingDesirabilityObjective,
     MaximizeObjective,
     MaximizeSigmoidObjective,
     MinimizeObjective,
     MinimizeSigmoidObjective,
     MovingMaximizeSigmoidObjective,
     Objective,
+    PeakDesirabilityObjective,
     TargetObjective,
 )
 from bofire.strategies.strategy import Strategy
@@ -431,6 +434,86 @@ def get_objective_callable(
                 )
             )
         )
+
+    if isinstance(objective, IncreasingDesirabilityObjective):
+
+        def objective_callable_(x: Tensor, *args) -> Tensor:
+            x = x[..., idx]
+
+            y = torch.zeros(x.shape, dtype=x.dtype, device=x.device)
+            if objective.clip:
+                y[x < objective.lower_bound] = 0.0
+                y[x > objective.upper_bound] = 1.0
+                between = (x >= objective.lower_bound) & (x <= objective.upper_bound)
+            else:
+                between = torch.full(x.shape, True, dtype=torch.bool, device=x.device)
+
+            t: float = np.exp(objective.log_shape_factor)
+
+            y[between] = torch.pow(
+                (x[between] - objective.lower_bound)
+                / (objective.upper_bound - objective.lower_bound),
+                t,
+            )
+            return y
+
+        return objective_callable_
+
+    if isinstance(objective, DecreasingDesirabilityObjective):
+
+        def objective_callable_(x: Tensor, *args) -> Tensor:
+            x = x[..., idx]
+
+            y = torch.zeros(x.shape, dtype=x.dtype, device=x.device)
+            if objective.clip:
+                y[x < objective.lower_bound] = 1.0
+                y[x > objective.upper_bound] = 0.0
+                between = (x >= objective.lower_bound) & (x <= objective.upper_bound)
+            else:
+                between = torch.full(x.shape, True, dtype=torch.bool, device=x.device)
+
+            t: float = np.exp(objective.log_shape_factor)
+            y[between] = torch.pow(
+                (objective.upper_bound - x[between])
+                / (objective.upper_bound - objective.lower_bound),
+                t,
+            )
+            return y
+
+        return objective_callable_
+
+    if isinstance(objective, PeakDesirabilityObjective):
+
+        def objective_callable_(x: Tensor, *args) -> Tensor:
+            x = x[..., idx]
+            y = torch.zeros(x.shape, dtype=x.dtype, device=x.device)
+
+            if objective.clip:
+                Incr = (x >= objective.lower_bound) & (x <= objective.peak_position)
+                Decr = (x <= objective.upper_bound) & (x > objective.peak_position)
+            else:
+                Incr, Decr = x <= objective.peak_position, x > objective.peak_position
+
+            s: float = np.exp(objective.log_shape_factor)
+            t: float = np.exp(objective.log_shape_factor_decreasing)
+            y[Incr] = torch.pow(
+                torch.divide(
+                    (x[Incr] - objective.lower_bound),
+                    (objective.peak_position - objective.lower_bound),
+                ),
+                s,
+            )
+            y[Decr] = torch.pow(
+                torch.divide(
+                    (x[Decr] - objective.upper_bound),
+                    (objective.peak_position - objective.upper_bound),
+                ),
+                t,
+            )
+            return y * objective.w
+
+        return objective_callable_
+
     raise NotImplementedError(
         f"Objective {objective.__class__.__name__} not implemented.",
     )
diff --git a/tests/bofire/data_models/specs/objectives.py b/tests/bofire/data_models/specs/objectives.py
index 2539590a..6a3d7885 100644
--- a/tests/bofire/data_models/specs/objectives.py
+++ b/tests/bofire/data_models/specs/objectives.py
@@ -82,3 +82,64 @@
     error=ValueError,
     message="Categories must be unique",
 )
+
+for obj in [
+    objectives.IncreasingDesirabilityObjective,
+    objectives.DecreasingDesirabilityObjective,
+]:
+    specs.add_valid(
+        obj,
+        lambda: {"w": 1.0, "bounds": [0, 10.0], "log_shape_factor": 1.0, "clip": True},
+    )
+    specs.add_valid(
+        obj,
+        lambda: {"w": 1.0, "bounds": [0, 10.0], "log_shape_factor": -1.0, "clip": True},
+    )
+    specs.add_invalid(
+        obj,
+        lambda: {
+            "w": 1.0,
+            "bounds": [0, 10.0],
+            "log_shape_factor": -1.0,
+            "clip": False,
+        },
+        ValueError,
+        "Log shape factor log_shape_factor must be zero if clip is False.",
+    )
+
+specs.add_valid(
+    objectives.PeakDesirabilityObjective,
+    lambda: {
+        "w": 1.0,
+        "bounds": [0, 10.0],
+        "clip": True,
+        "log_shape_factor": 0.0,
+        "log_shape_factor_decreasing": 0.0,
+        "peak_position": 5.0,
+    },
+)
+specs.add_invalid(
+    objectives.PeakDesirabilityObjective,
+    lambda: {
+        "w": 1.0,
+        "bounds": [0, 10.0],
+        "clip": False,
+        "log_shape_factor": 0.0,
+        "log_shape_factor_decreasing": 1.0,
+        "peak_position": 5.0,
+    },
+    ValueError,
+    "Log shape factor log_shape_factor_decreasing must be zero if clip is False.",
+)
+specs.add_invalid(
+    objectives.PeakDesirabilityObjective,
+    lambda: {"bounds": [0, 10.0], "peak_position": 15.0},
+    ValueError,
+    "Peak position must be within bounds",
+)
+specs.add_invalid(
+    objectives.PeakDesirabilityObjective,
+    lambda: {"bounds": [0, 10.0], "peak_position": -1.0},
+    ValueError,
+    "Peak position must be within bounds",
+)
diff --git a/tests/bofire/utils/test_torch_tools.py b/tests/bofire/utils/test_torch_tools.py
index dbdd1688..8b6dce0b 100644
--- a/tests/bofire/utils/test_torch_tools.py
+++ b/tests/bofire/utils/test_torch_tools.py
@@ -26,11 +26,14 @@
 from bofire.data_models.objectives.api import (
     CloseToTargetObjective,
     ConstrainedCategoricalObjective,
+    DecreasingDesirabilityObjective,
+    IncreasingDesirabilityObjective,
     MaximizeObjective,
     MaximizeSigmoidObjective,
     MinimizeObjective,
     MinimizeSigmoidObjective,
     MovingMaximizeSigmoidObjective,
+    PeakDesirabilityObjective,
     TargetObjective,
 )
 from bofire.data_models.strategies.api import RandomStrategy
@@ -109,6 +112,14 @@
         CloseToTargetObjective(target_value=2.0, exponent=1.0, w=0.5),
         MovingMaximizeSigmoidObjective(steepness=1, tp=-1, w=1),
         # ConstantObjective(w=0.5, value=1.0),
+        IncreasingDesirabilityObjective(
+            bounds=(0, 2.5), log_shape_factor=0.0, clip=False
+        ),
+        IncreasingDesirabilityObjective(
+            bounds=(0, 2.5), log_shape_factor=1.0, clip=True
+        ),
+        DecreasingDesirabilityObjective(bounds=(0, 5.0), log_shape_factor=1.0),
+        PeakDesirabilityObjective(bounds=(0, 5.0), peak_position=2.5),
     ],
 )
 def test_get_objective_callable(objective):
diff --git a/tutorials/advanced_examples/desirability_objectives.ipynb b/tutorials/advanced_examples/desirability_objectives.ipynb
new file mode 100644
index 00000000..cabe9658
--- /dev/null
+++ b/tutorials/advanced_examples/desirability_objectives.ipynb
@@ -0,0 +1,224 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "0",
+   "metadata": {},
+   "source": [
+    "# Desirability Functions for Multi-Objective Optimization\n",
+    "This notebook demonstrates the use of desirability functions for multi-objective optimization. The desirability function is a scalar function that maps a vector of objective values to a scalar value, most often in the range [0, 1]. The desirability function is used to aggregate multiple objectives into a single objective value, e.g. by the multiplicative Sobo strategy.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "\n",
+    "from bofire.data_models.objectives import api as objectives_data_model"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2",
+   "metadata": {},
+   "source": [
+    "### Desirability Functions map from the input space to the range [0, 1], also by clipping after the bounds"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "objectives = {\n",
+    "    \"Increasing\": objectives_data_model.IncreasingDesirabilityObjective(\n",
+    "        bounds=(0.0, 5.0)\n",
+    "    ),\n",
+    "    \"Decreasing\": objectives_data_model.DecreasingDesirabilityObjective(\n",
+    "        bounds=(0.0, 5.0)\n",
+    "    ),\n",
+    "    \"Peak\": objectives_data_model.PeakDesirabilityObjective(\n",
+    "        bounds=(0.0, 5.0), peak_position=2.5\n",
+    "    ),\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.legend.Legend at 0x17f83c590>"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "for key, objective in objectives.items():\n",
+    "    x = np.linspace(-2.0, 7.0, 100)\n",
+    "    y = objective(x, None)\n",
+    "    plt.plot(x, y, label=key)\n",
+    "plt.grid(True)\n",
+    "plt.legend()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5",
+   "metadata": {},
+   "source": [
+    "### Clipping is optional, but leads to values outside the [0, 1] range"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.legend.Legend at 0x30ad861b0>"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "objectives = {\n",
+    "    \"Increasing\": objectives_data_model.IncreasingDesirabilityObjective(\n",
+    "        bounds=(0.0, 5.0), clip=False\n",
+    "    ),\n",
+    "    \"Decreasing\": objectives_data_model.DecreasingDesirabilityObjective(\n",
+    "        bounds=(0.0, 5.0), clip=False\n",
+    "    ),\n",
+    "    \"Peak\": objectives_data_model.PeakDesirabilityObjective(\n",
+    "        bounds=(0.0, 5.0), peak_position=2.5, clip=False\n",
+    "    ),\n",
+    "}\n",
+    "for key, objective in objectives.items():\n",
+    "    x = np.linspace(-2.0, 7.0, 100)\n",
+    "    y = objective(x, None)\n",
+    "    plt.plot(x, y, label=key)\n",
+    "plt.grid(True)\n",
+    "plt.legend()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7",
+   "metadata": {},
+   "source": [
+    "### A concave or convex desirability function can be created by setting the `log_shape_factor`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.legend.Legend at 0x30ad4b020>"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "objectives = {\n",
+    "    \"Increasing\": objectives_data_model.IncreasingDesirabilityObjective(\n",
+    "        bounds=(0.0, 5.0), log_shape_factor=1.0\n",
+    "    ),\n",
+    "    \"Decreasing\": objectives_data_model.DecreasingDesirabilityObjective(\n",
+    "        bounds=(0.0, 5.0), log_shape_factor=-1.0\n",
+    "    ),\n",
+    "    \"Peak\": objectives_data_model.PeakDesirabilityObjective(\n",
+    "        bounds=(0.0, 5.0),\n",
+    "        peak_position=2.5,\n",
+    "        log_shape_factor=-1.0,\n",
+    "        log_shape_factor_decreasing=1.0,\n",
+    "    ),\n",
+    "}\n",
+    "for key, objective in objectives.items():\n",
+    "    x = np.linspace(-2.0, 7.0, 100)\n",
+    "    y = objective(x, None)\n",
+    "    plt.plot(x, y, label=key)\n",
+    "plt.grid(True)\n",
+    "plt.legend()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}