From 296fe0f83593562b07ae5cc7822ced1af3bec29a Mon Sep 17 00:00:00 2001 From: Zach Tilev <103522279+zachtil@users.noreply.github.com> Date: Mon, 29 Apr 2024 15:58:45 +0300 Subject: [PATCH] Update conditional-generation.ipynb --- conditional-generation/conditional-generation.ipynb | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/conditional-generation/conditional-generation.ipynb b/conditional-generation/conditional-generation.ipynb index f3d376f..e8f140f 100644 --- a/conditional-generation/conditional-generation.ipynb +++ b/conditional-generation/conditional-generation.ipynb @@ -353,7 +353,6 @@ "source": [ "from mostlyai import MostlyAI\n", "import pandas as pd\n", - "from sklearn.model_selection import train_test_split\n", "\n", "# fetch original data\n", "df = pd.read_csv('https://github.com/mostly-ai/public-demo-data/raw/dev/census/census.csv.gz')\n", @@ -1621,7 +1620,7 @@ "source": [ "### Explore Synthetic Data\n", "\n", - "Let's compare the price distribution across Manhatten. Note again, that while the locations in the partially synthetic data are actual locations, all other attributes, incl. the price per night, are randomly sampled by the generative model. Still, these prices are again statistically representative given the context, i.e. the location within Manhattan." + "Let's compare the price distribution across Manhattan. Note again, that while the locations in the partially synthetic data are actual locations, all other attributes, incl. the price per night, are randomly sampled by the generative model. Still, these prices are again statistically representative given the context, i.e. the location within Manhattan." ] }, { @@ -1654,7 +1653,7 @@ ], "source": [ "%%capture --no-display\n", - "def plot_manhatten(df, title):\n", + "def plot_manhattan(df, title):\n", " ax = df_orig.plot.scatter(\n", " x='longitude', \n", " y='latitude', \n", @@ -1667,8 +1666,8 @@ " ax.set_title(title)\n", " plt.show()\n", " \n", - "plot_manhatten(df_orig, 'Original Data')\n", - "plot_manhatten(syn_partial, 'Partially Synthetic Data')" + "plot_manhattan(df_orig, 'Original Data')\n", + "plot_manhattan(syn_partial, 'Partially Synthetic Data')" ] }, {