starting colclutions

analysis.ipynb

@@ -232,6 +232,75 @@
         "    ax.set_title(column)"
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "def correlation_fn(index: int):\n",
+        "    vectors = vectors_df.loc[index, 'vectors']\n",
+        "    weighted_vectors = vectors_df.loc[index, 'weighted_vectors']\n",
+        "    reduced_vectors = vectors_df.loc[index, 'reduced_vectors']\n",
+        "    reduced_weighted_vectors = vectors_df.loc[index, 'reduced_weighted_vectors']\n",
+        "    return {\n",
+        "        'vectors vs weighted_vectors': pearsonr(vectors, weighted_vectors),\n",
+        "        'vectors vs reduced_vectors': pearsonr(vectors, reduced_vectors),\n",
+        "        'vectors vs reduced_weighted_vectors': pearsonr(vectors, reduced_weighted_vectors),\n",
+        "        'weighted_vectors vs reduced_vectors': pearsonr(weighted_vectors, reduced_vectors),\n",
+        "        'weighted_vectors vs reduced_weighted_vectors': pearsonr(weighted_vectors, reduced_weighted_vectors),\n",
+        "        'reduced_vectors vs reduced_weighted_vectors': pearsonr(reduced_vectors, reduced_weighted_vectors),\n",
+        "    }\n",
+        "\n",
+        "correlation_results_2 = [correlation_fn(i) for i in tqdm.tqdm(range(len(vectors_df)))]"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import matplotlib.pyplot as plt\n",
+        "\n",
+        "columns = list(correlation_results_2[0].keys())\n",
+        "fig, axes = plt.subplots(6, 2, figsize=(24, 24))\n",
+        "axes = axes.flatten()\n",
+        "for i, column in enumerate(columns):\n",
+        "    ax = axes[i]\n",
+        "    corr = [j[column][0] for j in correlation_results_2]\n",
+        "    pvalues = [j[column][1] for j in correlation_results_2]\n",
+        "    # ax.hist([j[column][0] for j in correlation_results_2], bins=100)\n",
+        "    ax.plot(range(0, len(corr)), corr, label='Correlation', color='blue')\n",
+        "    # ax.plot(range(0, len(pvalues)), pvalues, label='pvalues', color='red')\n",
+        "    ax.set_title(column)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import matplotlib.pyplot as plt\n",
+        "\n",
+        "columns = list(correlation_results_2[0].keys())\n",
+        "fig, axes = plt.subplots(3, 2, figsize=(24, 24))\n",
+        "axes = axes.flatten()\n",
+        "for i, column in enumerate(columns):\n",
+        "    ax = axes[i]\n",
+        "    corr = [j[column][0] for j in correlation_results_2]\n",
+        "    pvalues = [j[column][1] for j in correlation_results_2]\n",
+        "    ax.plot(range(0, len(corr)), corr, label='correlation', color='blue')\n",
+        "    ax.plot(range(0, len(pvalues)), pvalues, label='p-value', color='red')\n",
+        "    ax.legend(bbox_to_anchor=(1, 0.1), loc='lower right')\n",
+        "    ax.set_ylabel('correlation & p-value')\n",
+        "    ax.set_xlabel(f'images - {column}')\n",
+        "    ax.set_title(column)\n",
+        "\n",
+        "fig.savefig('/Users/charleskabue/Downloads/vector-correlations.png')"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {},
@@ -428,6 +497,20 @@
         "        width_parts=100,\n",
         "        height_parts=100)"
       ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "<hr/>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": []
     }
   ],
   "metadata": {