Changed dataframe variable to df in all notebooks

Author: timmanik

01-cancer-data-analysis/completed-notebooks/fm-ad-notebook-exploration-COMPLETED.ipynb

@@ -389,10 +389,10 @@
     "        dataframes.append(df)\n",
     "\n",
     "# Concatenate all the dataframes in the list into a single dataframe\n",
-    "combined_df = pd.concat(dataframes, ignore_index=True)\n",
+    "df = pd.concat(dataframes, ignore_index=True)\n",
     "\n",
     "# Save dataframe to a CSV file\n",
-    "combined_df.to_csv('combined_data.csv', index=False)"
+    "df.to_csv('combined_data.csv', index=False)"
    ]
   },
   {
@@ -442,7 +442,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -830,14 +830,14 @@
        "4                      NaN                         NaN  "
       ]
      },
-     "execution_count": 9,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "# show first few records of the dataframe\n",
-    "combined_df.head()\n"
+    "df.head()"
    ]
   },
   {
@@ -856,7 +856,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -913,7 +913,7 @@
    ],
    "source": [
     "# get an overview of the dataframe\n",
-    "combined_df.info()"
+    "df.info()"
    ]
   },
   {
@@ -925,7 +925,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -934,17 +934,14 @@
        "(72016, 38)"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "# show the dataframe's dimensions\n",
-    "combined_df.shape\n",
-    "\n",
-    "\n",
-    "\n"
+    "df.shape"
    ]
   },
   {
@@ -956,7 +953,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -1003,14 +1000,14 @@
        "dtype: object"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "# show the columns and their data types\n",
-    "combined_df.dtypes"
+    "df.dtypes"
    ]
   },
   {
@@ -1024,7 +1021,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
@@ -1128,14 +1125,14 @@
        "max                       49.0  "
       ]
      },
-     "execution_count": 14,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "# show descriptive statistics of the dataframe\n",
-    "combined_df.describe()"
+    "df.describe()"
    ]
   },
   {
@@ -1154,7 +1151,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
@@ -1201,36 +1198,14 @@
        "dtype: int64"
       ]
      },
-     "execution_count": 16,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "# show the number of missing values in each column in descending order\n",
-    "combined_df.isnull().sum().sort_values(ascending=False)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['cases.submitter_id', 'case_id', 'cases.disease_type', 'cases.primary_site']"
-      ]
-     },
-     "execution_count": 17,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# show columns that start with 'case'\n",
-    "case_columns = [col for col in combined_df.columns if col.startswith('case')]\n",
-    "case_columns"
+    "df.isnull().sum().sort_values(ascending=False)"
    ]
   },
   {
@@ -1249,7 +1224,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 13,
    "metadata": {
     "slideshow": {
      "slide_type": "slide"
@@ -1266,14 +1241,14 @@
        "dtype: int64"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "# show which columns have the value 'Unknown' in them and show how many each column has in descending order\n",
-    "unknown_values = combined_df.isin(['Unknown']).sum().sort_values(ascending=False)\n",
+    "unknown_values = df.isin(['Unknown']).sum().sort_values(ascending=False)\n",
     "unknown_values[unknown_values > 0]"
    ]
   },
@@ -1293,7 +1268,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [
     {
@@ -1340,14 +1315,14 @@
        "dtype: int64"
       ]
      },
-     "execution_count": 21,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "# show the number of unique values in each column in descending order\n",
-    "unique_values = combined_df.nunique().sort_values(ascending=False)\n",
+    "unique_values = df.nunique().sort_values(ascending=False)\n",
     "unique_values"
    ]
   },
@@ -1360,7 +1335,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
@@ -1400,7 +1375,7 @@
     "# show 5 unique values of columns with unique values less than 100\n",
     "for col, n_unique in unique_values.items():\n",
     "    if n_unique < 100:\n",
-    "        unique_vals = combined_df[col].unique()\n",
+    "        unique_vals = df[col].unique()\n",
     "        print(f\"{col}: {unique_vals[:5]}\")"
    ]
   },
@@ -1420,7 +1395,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [
     {
@@ -1429,14 +1404,14 @@
        "36008"
       ]
      },
-     "execution_count": 24,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "# show the number of duplicate records in the dataframe\n",
-    "n_duplicates = combined_df.duplicated().sum()\n",
+    "n_duplicates = df.duplicated().sum()\n",
     "n_duplicates"
    ]
   },
@@ -1451,7 +1426,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [
     {
@@ -19465,14 +19440,14 @@
        "Name: count, dtype: int64"
       ]
      },
-     "execution_count": 28,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "# count how many records share the same case_id\n",
-    "case_id_counts = combined_df['case_id'].value_counts()\n",
+    "case_id_counts = df['case_id'].value_counts()\n",
     "case_id_counts"
    ]
   },
@@ -19485,7 +19460,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [
     {
@@ -19834,7 +19809,7 @@
        "36299                      NaN                         NaN  "
       ]
      },
-     "execution_count": 29,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -19843,7 +19818,7 @@
     "# show the records with the case_id 40e57344-a8ad-4de4-92e4-6e681c0593b7\n",
     "case_id = '40e57344-a8ad-4de4-92e4-6e681c0593b7'\n",
     "\n",
-    "combined_df[combined_df['case_id'] == '40e57344-a8ad-4de4-92e4-6e681c0593b7']"
+    "df[df['case_id'] == '40e57344-a8ad-4de4-92e4-6e681c0593b7']"
    ]
   },
   {