updates with Matt
This commit is contained in:
@@ -15,7 +15,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"execution_count": 18,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -26,7 +26,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": 19,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -41,7 +41,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"execution_count": 20,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -51,7 +51,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"execution_count": 21,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -62,7 +62,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"execution_count": 22,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@@ -78,7 +78,7 @@
|
||||
" dtype='object', length=194)"
|
||||
]
|
||||
},
|
||||
"execution_count": 11,
|
||||
"execution_count": 22,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -91,7 +91,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"execution_count": 23,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@@ -119,7 +119,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"execution_count": 24,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@@ -531,7 +531,7 @@
|
||||
"[409 rows x 194 columns]"
|
||||
]
|
||||
},
|
||||
"execution_count": 15,
|
||||
"execution_count": 24,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -543,7 +543,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"execution_count": 25,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -553,7 +553,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"execution_count": 26,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@@ -576,7 +576,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 19,
|
||||
"execution_count": 27,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -589,14 +589,14 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 20,
|
||||
"execution_count": 28,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/tmp/ipykernel_3460201/3570709754.py:7: FutureWarning: The provided callable <function sum at 0x7cfd6910e980> is currently using DataFrameGroupBy.sum. In a future version of pandas, the provided callable will be used directly. To keep current behavior pass the string \"sum\" instead.\n",
|
||||
"/tmp/ipykernel_2135561/3570709754.py:7: FutureWarning: The provided callable <function sum at 0x7f549753e8e0> is currently using DataFrameGroupBy.sum. In a future version of pandas, the provided callable will be used directly. To keep current behavior pass the string \"sum\" instead.\n",
|
||||
" pivot_table = pd.pivot_table(climate_investment, values='Total Project Cost', index='County_y', aggfunc=np.sum)\n"
|
||||
]
|
||||
},
|
||||
@@ -629,7 +629,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 22,
|
||||
"execution_count": 29,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@@ -645,7 +645,7 @@
|
||||
" dtype='object', length=194)"
|
||||
]
|
||||
},
|
||||
"execution_count": 22,
|
||||
"execution_count": 29,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -657,7 +657,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 28,
|
||||
"execution_count": 30,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -668,28 +668,380 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 29,
|
||||
"execution_count": 31,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# print the first 5 rows \n",
|
||||
"climate_investment.head().to_csv('first_5_rows.csv', index=False)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 33,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# frequency table for Project Description\n",
|
||||
"climate_investment['Project Description'].value_counts().to_csv('project_description_freq.csv')\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 38,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"0 None\n",
|
||||
"1 None\n",
|
||||
"2 None\n",
|
||||
"3 None\n",
|
||||
"4 None\n",
|
||||
"Name: Lat Long, dtype: object"
|
||||
"count 119356\n",
|
||||
"unique 2\n",
|
||||
"top False\n",
|
||||
"freq 90315\n",
|
||||
"Name: Is Benefit DAC1550Communities, dtype: object"
|
||||
]
|
||||
},
|
||||
"execution_count": 29,
|
||||
"execution_count": 38,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# head of column 'Lat Long' \n",
|
||||
"climate_investment['Lat Long'].head()\n"
|
||||
"climate_investment[\"Is Benefit DAC1550Communities\"].describe()\n",
|
||||
"\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 40,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div>\n",
|
||||
"<style scoped>\n",
|
||||
" .dataframe tbody tr th:only-of-type {\n",
|
||||
" vertical-align: middle;\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" .dataframe tbody tr th {\n",
|
||||
" vertical-align: top;\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" .dataframe thead th {\n",
|
||||
" text-align: right;\n",
|
||||
" }\n",
|
||||
"</style>\n",
|
||||
"<table border=\"1\" class=\"dataframe\">\n",
|
||||
" <thead>\n",
|
||||
" <tr style=\"text-align: right;\">\n",
|
||||
" <th></th>\n",
|
||||
" <th>ZIP</th>\n",
|
||||
" <th>TotPop19</th>\n",
|
||||
" <th>CIscore</th>\n",
|
||||
" <th>CIscoreP</th>\n",
|
||||
" <th>Ozone</th>\n",
|
||||
" <th>OzoneP</th>\n",
|
||||
" <th>PM2_5</th>\n",
|
||||
" <th>PM2_5_P</th>\n",
|
||||
" <th>DieselPM</th>\n",
|
||||
" <th>DieselPM_P</th>\n",
|
||||
" <th>...</th>\n",
|
||||
" <th>Indirect Jobs Fte</th>\n",
|
||||
" <th>Induced Jobs Fte</th>\n",
|
||||
" <th>Compost Produced Tons</th>\n",
|
||||
" <th>Compost Produced Tons Yr</th>\n",
|
||||
" <th>Net Density DUA</th>\n",
|
||||
" <th>Applicants Assisted</th>\n",
|
||||
" <th>Invasive Cover 12 Months</th>\n",
|
||||
" <th>Invasive Cover 36 Months</th>\n",
|
||||
" <th>Project Acreage</th>\n",
|
||||
" <th>Intermediary Admin Expenses Calc</th>\n",
|
||||
" </tr>\n",
|
||||
" </thead>\n",
|
||||
" <tbody>\n",
|
||||
" <tr>\n",
|
||||
" <th>count</th>\n",
|
||||
" <td>119356.000000</td>\n",
|
||||
" <td>119356.000000</td>\n",
|
||||
" <td>119356.000000</td>\n",
|
||||
" <td>119356.000000</td>\n",
|
||||
" <td>119356.000000</td>\n",
|
||||
" <td>119356.000000</td>\n",
|
||||
" <td>119356.000000</td>\n",
|
||||
" <td>119356.000000</td>\n",
|
||||
" <td>119356.000000</td>\n",
|
||||
" <td>119356.000000</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>119356.0</td>\n",
|
||||
" <td>119356.0</td>\n",
|
||||
" <td>119356.000000</td>\n",
|
||||
" <td>119356.0</td>\n",
|
||||
" <td>119356.0</td>\n",
|
||||
" <td>119356.0</td>\n",
|
||||
" <td>119356.0</td>\n",
|
||||
" <td>119356.0</td>\n",
|
||||
" <td>119356.0</td>\n",
|
||||
" <td>1.193560e+05</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>mean</th>\n",
|
||||
" <td>92876.728577</td>\n",
|
||||
" <td>5309.716411</td>\n",
|
||||
" <td>23.935192</td>\n",
|
||||
" <td>45.734280</td>\n",
|
||||
" <td>0.048625</td>\n",
|
||||
" <td>50.911545</td>\n",
|
||||
" <td>10.405602</td>\n",
|
||||
" <td>53.148956</td>\n",
|
||||
" <td>0.240707</td>\n",
|
||||
" <td>52.309922</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.022881</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>1.059589e+03</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>std</th>\n",
|
||||
" <td>2343.339535</td>\n",
|
||||
" <td>2527.349328</td>\n",
|
||||
" <td>71.431858</td>\n",
|
||||
" <td>76.628615</td>\n",
|
||||
" <td>0.010285</td>\n",
|
||||
" <td>28.485539</td>\n",
|
||||
" <td>2.077885</td>\n",
|
||||
" <td>28.427845</td>\n",
|
||||
" <td>0.338975</td>\n",
|
||||
" <td>28.401653</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>1.627501</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>8.701853e+04</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>min</th>\n",
|
||||
" <td>32.000000</td>\n",
|
||||
" <td>0.000000</td>\n",
|
||||
" <td>-999.000000</td>\n",
|
||||
" <td>-999.000000</td>\n",
|
||||
" <td>0.026554</td>\n",
|
||||
" <td>0.186683</td>\n",
|
||||
" <td>1.875092</td>\n",
|
||||
" <td>0.012446</td>\n",
|
||||
" <td>0.000214</td>\n",
|
||||
" <td>0.037337</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.000000</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.000000e+00</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>25%</th>\n",
|
||||
" <td>91506.000000</td>\n",
|
||||
" <td>3758.000000</td>\n",
|
||||
" <td>14.757710</td>\n",
|
||||
" <td>24.911750</td>\n",
|
||||
" <td>0.041252</td>\n",
|
||||
" <td>24.878656</td>\n",
|
||||
" <td>8.659819</td>\n",
|
||||
" <td>28.357187</td>\n",
|
||||
" <td>0.075040</td>\n",
|
||||
" <td>27.940261</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.000000</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.000000e+00</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>50%</th>\n",
|
||||
" <td>92691.000000</td>\n",
|
||||
" <td>4943.000000</td>\n",
|
||||
" <td>26.049788</td>\n",
|
||||
" <td>51.033787</td>\n",
|
||||
" <td>0.047536</td>\n",
|
||||
" <td>50.989421</td>\n",
|
||||
" <td>11.021278</td>\n",
|
||||
" <td>55.084007</td>\n",
|
||||
" <td>0.157610</td>\n",
|
||||
" <td>53.005600</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.000000</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.000000e+00</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>75%</th>\n",
|
||||
" <td>94558.000000</td>\n",
|
||||
" <td>6345.000000</td>\n",
|
||||
" <td>40.367234</td>\n",
|
||||
" <td>75.617751</td>\n",
|
||||
" <td>0.056800</td>\n",
|
||||
" <td>75.121344</td>\n",
|
||||
" <td>11.983522</td>\n",
|
||||
" <td>77.523335</td>\n",
|
||||
" <td>0.308042</td>\n",
|
||||
" <td>77.349098</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.000000</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.000000e+00</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>max</th>\n",
|
||||
" <td>96161.000000</td>\n",
|
||||
" <td>38754.000000</td>\n",
|
||||
" <td>93.183570</td>\n",
|
||||
" <td>100.000000</td>\n",
|
||||
" <td>0.073132</td>\n",
|
||||
" <td>100.000000</td>\n",
|
||||
" <td>16.394748</td>\n",
|
||||
" <td>100.000000</td>\n",
|
||||
" <td>14.611221</td>\n",
|
||||
" <td>100.000000</td>\n",
|
||||
" <td>...</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>306.000000</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>0.0</td>\n",
|
||||
" <td>1.923000e+07</td>\n",
|
||||
" </tr>\n",
|
||||
" </tbody>\n",
|
||||
"</table>\n",
|
||||
"<p>8 rows × 141 columns</p>\n",
|
||||
"</div>"
|
||||
],
|
||||
"text/plain": [
|
||||
" ZIP TotPop19 CIscore CIscoreP \\\n",
|
||||
"count 119356.000000 119356.000000 119356.000000 119356.000000 \n",
|
||||
"mean 92876.728577 5309.716411 23.935192 45.734280 \n",
|
||||
"std 2343.339535 2527.349328 71.431858 76.628615 \n",
|
||||
"min 32.000000 0.000000 -999.000000 -999.000000 \n",
|
||||
"25% 91506.000000 3758.000000 14.757710 24.911750 \n",
|
||||
"50% 92691.000000 4943.000000 26.049788 51.033787 \n",
|
||||
"75% 94558.000000 6345.000000 40.367234 75.617751 \n",
|
||||
"max 96161.000000 38754.000000 93.183570 100.000000 \n",
|
||||
"\n",
|
||||
" Ozone OzoneP PM2_5 PM2_5_P \\\n",
|
||||
"count 119356.000000 119356.000000 119356.000000 119356.000000 \n",
|
||||
"mean 0.048625 50.911545 10.405602 53.148956 \n",
|
||||
"std 0.010285 28.485539 2.077885 28.427845 \n",
|
||||
"min 0.026554 0.186683 1.875092 0.012446 \n",
|
||||
"25% 0.041252 24.878656 8.659819 28.357187 \n",
|
||||
"50% 0.047536 50.989421 11.021278 55.084007 \n",
|
||||
"75% 0.056800 75.121344 11.983522 77.523335 \n",
|
||||
"max 0.073132 100.000000 16.394748 100.000000 \n",
|
||||
"\n",
|
||||
" DieselPM DieselPM_P ... Indirect Jobs Fte Induced Jobs Fte \\\n",
|
||||
"count 119356.000000 119356.000000 ... 119356.0 119356.0 \n",
|
||||
"mean 0.240707 52.309922 ... 0.0 0.0 \n",
|
||||
"std 0.338975 28.401653 ... 0.0 0.0 \n",
|
||||
"min 0.000214 0.037337 ... 0.0 0.0 \n",
|
||||
"25% 0.075040 27.940261 ... 0.0 0.0 \n",
|
||||
"50% 0.157610 53.005600 ... 0.0 0.0 \n",
|
||||
"75% 0.308042 77.349098 ... 0.0 0.0 \n",
|
||||
"max 14.611221 100.000000 ... 0.0 0.0 \n",
|
||||
"\n",
|
||||
" Compost Produced Tons Compost Produced Tons Yr Net Density DUA \\\n",
|
||||
"count 119356.000000 119356.0 119356.0 \n",
|
||||
"mean 0.022881 0.0 0.0 \n",
|
||||
"std 1.627501 0.0 0.0 \n",
|
||||
"min 0.000000 0.0 0.0 \n",
|
||||
"25% 0.000000 0.0 0.0 \n",
|
||||
"50% 0.000000 0.0 0.0 \n",
|
||||
"75% 0.000000 0.0 0.0 \n",
|
||||
"max 306.000000 0.0 0.0 \n",
|
||||
"\n",
|
||||
" Applicants Assisted Invasive Cover 12 Months \\\n",
|
||||
"count 119356.0 119356.0 \n",
|
||||
"mean 0.0 0.0 \n",
|
||||
"std 0.0 0.0 \n",
|
||||
"min 0.0 0.0 \n",
|
||||
"25% 0.0 0.0 \n",
|
||||
"50% 0.0 0.0 \n",
|
||||
"75% 0.0 0.0 \n",
|
||||
"max 0.0 0.0 \n",
|
||||
"\n",
|
||||
" Invasive Cover 36 Months Project Acreage \\\n",
|
||||
"count 119356.0 119356.0 \n",
|
||||
"mean 0.0 0.0 \n",
|
||||
"std 0.0 0.0 \n",
|
||||
"min 0.0 0.0 \n",
|
||||
"25% 0.0 0.0 \n",
|
||||
"50% 0.0 0.0 \n",
|
||||
"75% 0.0 0.0 \n",
|
||||
"max 0.0 0.0 \n",
|
||||
"\n",
|
||||
" Intermediary Admin Expenses Calc \n",
|
||||
"count 1.193560e+05 \n",
|
||||
"mean 1.059589e+03 \n",
|
||||
"std 8.701853e+04 \n",
|
||||
"min 0.000000e+00 \n",
|
||||
"25% 0.000000e+00 \n",
|
||||
"50% 0.000000e+00 \n",
|
||||
"75% 0.000000e+00 \n",
|
||||
"max 1.923000e+07 \n",
|
||||
"\n",
|
||||
"[8 rows x 141 columns]"
|
||||
]
|
||||
},
|
||||
"execution_count": 40,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# summarize the dataframe\n",
|
||||
"climate_investment.describe()\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
Reference in New Issue
Block a user