diff --git a/src/notebooks/worc_cleaning.ipynb b/src/notebooks/worc_cleaning.ipynb index 267af60..1ed7f9b 100644 --- a/src/notebooks/worc_cleaning.ipynb +++ b/src/notebooks/worc_cleaning.ipynb @@ -418,7 +418,7 @@ "outputs": [], "source": [ "# Dropping multiple columns based including those with no unique values as well as those that seem unnecessary\n", - "cols_to_drop = ['Auto Id','Employment History Name']\n", + "cols_to_drop = ['Employment History Name']\n", "\n", "worc_cols_dropped = worc.drop(columns=cols_to_drop, axis=1)" ] diff --git a/src/notebooks/worc_employment_clean.xlsx b/src/notebooks/worc_employment_clean.xlsx index cfd8a08..151ff8b 100644 Binary files a/src/notebooks/worc_employment_clean.xlsx and b/src/notebooks/worc_employment_clean.xlsx differ diff --git a/src/notebooks/worc_employment_plots.ipynb b/src/notebooks/worc_employment_plots.ipynb index 643170e..d927097 100644 --- a/src/notebooks/worc_employment_plots.ipynb +++ b/src/notebooks/worc_employment_plots.ipynb @@ -45,7 +45,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 3, "metadata": {}, "outputs": [ { @@ -211,7 +211,7 @@ "24 First ATP Placement - Already in Tech 23.83 Female White SOAR " ] }, - "execution_count": 4, + "execution_count": 3, "metadata": {}, "output_type": "execute_result" } @@ -240,7 +240,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 4, "metadata": {}, "outputs": [], "source": [ @@ -253,7 +253,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 5, "metadata": {}, "outputs": [ { @@ -339,7 +339,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 6, "metadata": {}, "outputs": [ { @@ -364,7 +364,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 7, "metadata": {}, "outputs": [ { @@ -398,14 +398,14 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ - "/var/folders/sw/mf1x4fnn1jg2jq5n72k6mkm80000gn/T/ipykernel_25780/1675383775.py:2: FutureWarning: 'M' is deprecated and will be removed in a future version, please use 'ME' instead.\n", + "/var/folders/sw/mf1x4fnn1jg2jq5n72k6mkm80000gn/T/ipykernel_4812/1675383775.py:2: FutureWarning: 'M' is deprecated and will be removed in a future version, please use 'ME' instead.\n", " worc_clean.set_index('Start Date').resample('M').size().plot(kind='line', marker='o', figsize=(10, 4))\n" ] }, @@ -430,7 +430,7 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 9, "metadata": {}, "outputs": [ { @@ -455,7 +455,7 @@ }, { "cell_type": "code", - "execution_count": 29, + "execution_count": 10, "metadata": {}, "outputs": [ { @@ -479,7 +479,58 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": 11, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Gender\n", + "Male 13\n", + "Female 12\n", + "Name: count, dtype: int64" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Count of Gender\n", + "worc_clean['Gender'].value_counts()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "ATP Placement Type Gender\n", + "First ATP Placement - Already in Tech Female 2\n", + " Male 1\n", + "First ATP Placement - New to Tech Female 9\n", + " Male 9\n", + "First ATP Placement - Promotion Female 1\n", + " Male 3\n", + "dtype: int64\n" + ] + } + ], + "source": [ + " # Count of gender by ATP Placement Type\n", + "grouped = worc_clean.groupby(['ATP Placement Type', 'Gender']).size()\n", + "\n", + "print(grouped)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 13, "metadata": {}, "outputs": [], "source": [