daviddoji/pytudes
1
0 Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add files via upload

Browse Source
This commit is contained in:
Peter Norvig authored and GitHub committed 2019-07-03 20:16:03 -07:00
1 parent eb617de07c
commit e5d52dc278
1 file changed
+130 -134
Download Patch File Download Diff File Expand all files Collapse all files
ipynb/Electoral Votes.ipynb
+130 -134
View File
@@ -22,7 +22,8 @@
"\n",
"# TL;DR for policy wonks\n",
"\n",
"As of 1 May 2019, Trump would expect **193 electoral votes** under these assumptions (recall that you need **270** to win). He's been below 270 every month for the last two years, and that remains true even if you factor in an across-the-board 3% swing in his favor (which was the swing above polls that he experienced in 2016).\n",
"As of 2 July 2019, Trump would expect **167 electoral votes** under these assumptions (recall that you need **270** to win). If you ran states in order of his approval, the key turning-point state is Pennsylvania; he'd need to win that and every state in which he is more popular. He currently is **9% behind in Pennsylvania**. \n",
"He's been below 270 every month for the last two years, and that remains true even if you factor in an across-the-board 3% swing in his favor (which was the swing above polls that he experienced in 2016).\n",
"\n",
"\n",
"# The details for data science nerds\n",
@@ -36,7 +37,7 @@
"\n",
"- **Movement**: What's the most a state's net approval could be expected to move, due to random fluctuations (that is, assuming there is no big event that changes people's minds)? I define the maximum expected **movement** of a state as 1/5 of the undecided voters (i.e. assume the undecided voters broke 60/40 one way or the other) plus 2 standard deviations in the net approval over the last 12 months. \n",
"\n",
"- **Swing state**: I define a swing state as one whose maximum expected movement is greater than the absolute value of the net approval. There are 15 such states now. My definition correlates well with the standard wisdom on swing states, but with a few surprises: North Dakota is included because Trump is currently only +1% net approval; a typical Republican is +30%. My model says that Pennsylvania, Michigan, and Wisconsin, which are traditionally considered swing states, are currently out of reach for Trump because they have low movement (3% to 5%) and Trump is currently at -7%, -12% and -13% respectively. If Trump won all the swing states he would get **253** electoral votes, and if he lost them all, **76** electoral votes.\n",
"- **Swing state**: I define a swing state as one whose maximum expected movement is greater than the absolute value of the net approval. There are 16 such states now; if Trump won them all, he would still lose the elction. Some states that are traditionally considered swing states are out of reach for Trump under my model: he currently trails in Pennsylvania by 9%, in Wisconsin by %14, and in Michigan by %15. My model says these states can be expected to move by no more than 5%. Some traditionally solid Republican states are swing states in my model, such as Texas, which has Trump at +4%, but has 4% undecided voters.\n",
"\n",
"- **Margin**: Suppose a future event swings voters in one direction or another uniformly, across the board in all states. How much of a swing would be necessary to change the election outcome? We call that the **margin**. Today **Trump's margin is 7%:** if he got 7% more votes in all states he would be over 270 electoral votes. (This could come, for example, by convincing the 3% of undecided voters to break for him at a 2% to 1% ratio, and then convincing 3% of disapproving voters to switch to approving.)\n",
"\n",
@@ -57,7 +58,7 @@
"text": [
" % Total % Received % Xferd Average Speed Time Time Time Current\n",
" Dload Upload Total Spent Left Speed\n",
"100 116k 0 116k 0 0 216k 0 --:--:-- --:--:-- --:--:-- 216k\n"
"100 116k 0 116k 0 0 15866 0 --:--:-- 0:00:07 --:--:-- 31316\n"
]
}
],
@@ -128,7 +129,8 @@
" '1-Feb-18': -15, '1-Mar-18': -14, '1-Apr-18': -13, '1-May-18': -12,\n",
" '1-Jun-18': -11, '1-Jul-18': -10, '1-Aug-18': -12, '1-Sep-18': -14,\n",
" '1-Oct-18': -11, '1-Nov-18': -11, '1-Dec-18': -10, '1-Jan-19': -12,\n",
" '1-Feb-19': -16, '1-Mar-19': -11, '1-Apr-19': -11, '1-May-19': -12}"
" '1-Feb-19': -16, '1-Mar-19': -11, '1-Apr-19': -11, '1-May-19': -12,\n",
" '1-Jun-19': -12}"
]
},
{
@@ -198,7 +200,7 @@
{
"data": {
"text/plain": [
"193.0"
"167.0"
]
},
"execution_count": 5,
@@ -207,26 +209,17 @@
}
],
"source": [
"# How many Electoral votes would Trump expect to get today?\n",
"EV(states)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"7"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"outputs": [],
"source": [
"# What across-the-board increase in percentage approval would he need to win?\n",
"margin(states)"
]
},
@@ -238,16 +231,17 @@
{
"data": {
"text/plain": [
"{0: 193.0,\n",
" 1: 209,\n",
" 2: 209,\n",
" 3: 209,\n",
" 4: 225.5,\n",
" 5: 242,\n",
" 6: 254.0,\n",
" 7: 276.0,\n",
" 8: 286,\n",
" 9: 288.0}"
"{0: 167.0,\n",
" 1: 180,\n",
" 2: 180,\n",
" 3: 202.0,\n",
" 4: 230.5,\n",
" 5: 237,\n",
" 6: 246.0,\n",
" 7: 260.5,\n",
" 8: 266,\n",
" 9: 277.5,\n",
" 10: 292.0}"
]
},
"execution_count": 7,
@@ -256,8 +250,9 @@
}
],
"source": [
"# How many votes does he get with various swings?\n",
"{swing: EV(states, now, swing)\n",
" for swing in range(10)}"
" for swing in range(11)}"
]
},
{
@@ -265,9 +260,9 @@
"metadata": {},
"source": [
"We see that:\n",
"- Trump is currently leading in states with only 193 electoral votes; \n",
"- The margin is 7% (if he got 7% more popular in every state, he would win a narrow 276 to 262 vote victory).\n",
"- Swings from 0 to 9% produce electoral vote totals from 193 to 288."
"- Trump is currently leading in states with only **167** electoral votes; \n",
"- The margin is **9%** (if he got 9% more popular in every state, his expected total would be over 270).\n",
"- Swings from 0 to 10% produce electoral vote totals from 167 to 292."
]
},
{
@@ -286,7 +281,7 @@
"outputs": [
{
"data": {
"image/png": "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 truncated
"image/png": "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 truncated
"text/plain": [
"<Figure size 864x720 with 1 Axes>"
]
@@ -329,7 +324,7 @@
"outputs": [
{
"data": {
"image/png": "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 truncated
"image/png": "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 truncated
"text/plain": [
"<Figure size 864x720 with 1 Axes>"
]
@@ -369,6 +364,7 @@
"text/markdown": [
"|Month|EVs|Margin|Country|Undecided|\n",
"|-|-|-|-|-|\n",
"|Jun 2019|167|9%|-12%|4% (1)|\n",
"|May 2019|193|7%|-12%|4% (1)|\n",
"|Apr 2019|180|7%|-11%|4% (0)|\n",
"|Mar 2019|193|7%|-11%|4% (2)|\n",
@@ -430,7 +426,7 @@
"source": [
"# State-by-state summary table\n",
"\n",
"Below is each state sorted by net approval, with the state's maximum expected movement, and electoral vote allotment, followed by the cumulative running total of electoral votes and the percentages of approval, disapprovalsaproval, and undecided, and finally the standard deviation of the net approval over the last 12 months. By going down the **Total** column, you can see what it takes to win. \n",
"Below is each state sorted by net approval, with the state's maximum expected movement, and electoral vote allotment, followed by the cumulative running total of electoral votes and the percentages of approval, disapprovals, and undecided in the state, and finally the standard deviation of the net approval over the last 12 months. By going down the **Total** column, you can see what it takes to win. \n",
"\n",
"The **CAPITALIZED bold state names** are the **swing states**, which I define as states in which the absolute value of net approval is less than two standard deviations of the net approval over time, plus a fifth of the undecided voters. The idea is that if we are just dealing with random sampling variation, you could expect future approval to be within two standard deviations 95% of the time, and if the undecideds split 60/40, then a candidate could get a net fifth of them. So it would be very unusual for the non-bold states to flip, unless some events change perception of the candidates.\n",
"\n",
@@ -447,57 +443,57 @@
"text/markdown": [
"|State|Net|Move|EV|Total|+|-|?|𝝈|\n",
"|-|-|-|-|-|-|-|-|-|\n",
"|Alabama|+27%|8%|9|9|61%|34%|5%|3.3%|\n",
"|Wyoming|+22%|9%|3|12|59%|37%|4%|4.1%|\n",
"|Idaho|+20%|5%|4|16|58%|38%|4%|2.3%|\n",
"|West Virginia|+18%|9%|5|21|57%|39%|4%|4.3%|\n",
"|Louisiana|+17%|8%|8|29|56%|39%|5%|3.5%|\n",
"|Mississippi|+17%|9%|6|35|56%|39%|5%|3.8%|\n",
"|Tennessee|+16%|7%|11|46|56%|40%|4%|3.1%|\n",
"|Kentucky|+14%|3%|8|54|55%|41%|4%|1.2%|\n",
"|South Carolina|+10%|5%|9|63|53%|43%|4%|2.1%|\n",
"|Oklahoma|+9%|8%|7|70|52%|43%|5%|3.5%|\n",
"|Arkansas|+8%|7%|6|76|52%|44%|4%|3.0%|\n",
"|**MISSOURI**|**+6%**|**7%**|10|86|51%|45%|4%|3.0%|\n",
"|**SOUTH DAKOTA**|**+6%**|**10%**|3|89|51%|45%|4%|4.5%|\n",
"|**INDIANA**|**+3%**|**5%**|11|100|49%|46%|5%|2.0%|\n",
"|**MONTANA**|**+3%**|**7%**|3|103|50%|47%|3%|3.4%|\n",
"|**TEXAS**|**+3%**|**6%**|38|141|49%|46%|5%|2.7%|\n",
"|**NEBRASKA**|**+2%**|**6%**|5|146|49%|47%|4%|2.8%|\n",
"|**UTAH**|**+2%**|**8%**|6|152|49%|47%|4%|3.6%|\n",
"|**GEORGIA**|**+1%**|**7%**|16|168|48%|47%|5%|2.9%|\n",
"|**KANSAS**|**+1%**|**7%**|6|174|48%|47%|5%|3.0%|\n",
"|**NORTH DAKOTA**|**+1%**|**8%**|3|177|48%|47%|5%|3.3%|\n",
"|**ALASKA**|**+0%**|**12%**|3|180|47%|47%|6%|5.5%|\n",
"|**FLORIDA**|**+0%**|**7%**|29|209|48%|48%|4%|3.1%|\n",
"|**NORTH CAROLINA**|**-4%**|**6%**|15|224|46%|50%|4%|2.4%|\n",
"|**OHIO**|**-4%**|**6%**|18|242|46%|50%|4%|2.4%|\n",
"|**ARIZONA**|**-6%**|**8%**|11|253|45%|51%|4%|3.4%|\n",
"|Virginia|-6%|4%|13|266|45%|51%|4%|1.8%|\n",
"|Pennsylvania|-7%|3%|20|286|45%|52%|3%|1.4%|\n",
"|Maine|-9%|8%|4|290|44%|53%|3%|3.9%|\n",
"|Nevada|-11%|7%|6|296|42%|53%|5%|2.8%|\n",
"|Iowa|-12%|6%|6|302|42%|54%|4%|2.7%|\n",
"|Michigan|-12%|5%|16|318|42%|54%|4%|2.1%|\n",
"|Wisconsin|-13%|5%|10|328|42%|55%|3%|2.4%|\n",
"|Colorado|-14%|5%|9|337|41%|55%|4%|2.3%|\n",
"|Delaware|-15%|4%|3|340|41%|56%|3%|1.9%|\n",
"|New Mexico|-15%|6%|5|345|41%|56%|3%|2.9%|\n",
"|Minnesota|-16%|5%|10|355|40%|56%|4%|2.2%|\n",
"|New Jersey|-18%|6%|14|369|39%|57%|4%|2.5%|\n",
"|New Hampshire|-19%|8%|4|373|39%|58%|3%|3.8%|\n",
"|Illinois|-20%|3%|20|393|38%|58%|4%|1.2%|\n",
"|Rhode Island|-20%|6%|4|397|38%|58%|4%|2.6%|\n",
"|New York|-22%|4%|29|426|37%|59%|4%|1.8%|\n",
"|Oregon|-22%|5%|7|433|37%|59%|4%|2.0%|\n",
"|Connecticut|-24%|9%|7|440|36%|60%|4%|3.9%|\n",
"|Massachusetts|-27%|5%|11|451|35%|62%|3%|2.1%|\n",
"|California|-28%|6%|55|506|34%|62%|4%|2.7%|\n",
"|Washington|-30%|6%|12|518|33%|63%|4%|2.5%|\n",
"|Maryland|-31%|8%|10|528|33%|64%|3%|3.5%|\n",
"|Hawaii|-33%|10%|4|532|32%|65%|3%|4.5%|\n",
"|Vermont|-34%|10%|3|535|32%|66%|2%|4.9%|\n",
"|District of Columbia|-62%|7%|3|538|17%|79%|4%|3.1%|"
"|Alabama|+24%|7%|9|9|60%|36%|4%|3.2%|\n",
"|Wyoming|+22%|10%|3|12|59%|37%|4%|4.4%|\n",
"|West Virginia|+19%|10%|5|17|58%|39%|3%|4.7%|\n",
"|Idaho|+18%|5%|4|21|57%|39%|4%|2.3%|\n",
"|Mississippi|+18%|8%|6|27|57%|39%|4%|3.6%|\n",
"|Tennessee|+17%|7%|11|38|57%|40%|3%|3.0%|\n",
"|Kentucky|+15%|3%|8|46|56%|41%|3%|1.1%|\n",
"|Louisiana|+14%|8%|8|54|55%|41%|4%|3.6%|\n",
"|Oklahoma|+12%|8%|7|61|54%|42%|4%|3.4%|\n",
"|South Carolina|+8%|5%|9|70|52%|44%|4%|2.3%|\n",
"|**MONTANA**|**+7%**|**7%**|3|73|52%|45%|3%|3.3%|\n",
"|**ARKANSAS**|**+6%**|**7%**|6|79|51%|45%|4%|3.3%|\n",
"|**NORTH DAKOTA**|**+6%**|**7%**|3|82|51%|45%|4%|3.3%|\n",
"|**SOUTH DAKOTA**|**+4%**|**11%**|3|85|50%|46%|4%|4.9%|\n",
"|**TEXAS**|**+4%**|**5%**|38|123|50%|46%|4%|2.2%|\n",
"|**ALASKA**|**+3%**|**12%**|3|126|48%|45%|7%|5.4%|\n",
"|**KANSAS**|**+3%**|**7%**|6|132|50%|47%|3%|3.1%|\n",
"|**UTAH**|**+2%**|**8%**|6|138|49%|47%|4%|3.6%|\n",
"|**INDIANA**|**+1%**|**5%**|11|149|49%|48%|3%|2.3%|\n",
"|**NEBRASKA**|**+1%**|**7%**|5|154|49%|48%|3%|3.0%|\n",
"|**GEORGIA**|**+0%**|**6%**|16|170|48%|48%|4%|2.8%|\n",
"|**MISSOURI**|**+0%**|**8%**|10|180|48%|48%|4%|3.4%|\n",
"|**FLORIDA**|**-3%**|**6%**|29|209|47%|50%|3%|2.6%|\n",
"|**NORTH CAROLINA**|**-3%**|**5%**|15|224|47%|50%|3%|2.4%|\n",
"|**VIRGINIA**|**-4%**|**4%**|13|237|46%|50%|4%|1.8%|\n",
"|Ohio|-6%|6%|18|255|45%|51%|4%|2.5%|\n",
"|**ARIZONA**|**-7%**|**7%**|11|266|45%|52%|3%|3.3%|\n",
"|Delaware|-9%|5%|3|269|44%|53%|3%|2.4%|\n",
"|Pennsylvania|-9%|3%|20|289|44%|53%|3%|1.4%|\n",
"|Nevada|-10%|6%|6|295|43%|53%|4%|2.8%|\n",
"|Maine|-11%|7%|4|299|43%|54%|3%|3.0%|\n",
"|Colorado|-13%|5%|9|308|42%|55%|3%|2.3%|\n",
"|Iowa|-13%|5%|6|314|42%|55%|3%|2.4%|\n",
"|Wisconsin|-14%|5%|10|324|42%|56%|2%|2.4%|\n",
"|Michigan|-15%|5%|16|340|40%|55%|5%|2.0%|\n",
"|New Jersey|-15%|5%|14|354|41%|56%|3%|2.2%|\n",
"|Minnesota|-16%|5%|10|364|41%|57%|2%|2.2%|\n",
"|New Mexico|-16%|7%|5|369|40%|56%|4%|2.9%|\n",
"|Oregon|-19%|4%|7|376|39%|58%|3%|1.9%|\n",
"|Illinois|-20%|3%|20|396|38%|58%|4%|1.2%|\n",
"|Rhode Island|-21%|6%|4|400|38%|59%|3%|2.5%|\n",
"|Connecticut|-23%|7%|7|407|37%|60%|3%|3.3%|\n",
"|Hawaii|-23%|10%|4|411|37%|60%|3%|4.5%|\n",
"|New Hampshire|-23%|9%|4|415|37%|60%|3%|4.4%|\n",
"|New York|-25%|5%|29|444|36%|61%|3%|2.0%|\n",
"|Massachusetts|-27%|5%|11|455|35%|62%|3%|2.0%|\n",
"|Maryland|-28%|8%|10|465|34%|62%|4%|3.4%|\n",
"|Vermont|-28%|9%|3|468|35%|63%|2%|4.1%|\n",
"|Washington|-28%|6%|12|480|34%|62%|4%|2.5%|\n",
"|California|-29%|6%|55|535|33%|62%|5%|2.3%|\n",
"|District of Columbia|-59%|5%|3|538|19%|78%|3%|2.1%|"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
@@ -531,7 +527,7 @@
"\n",
"Fivethirtyeight is a combination sports/politics site, and it has a lot of statistics about sports players and how much better they are than the average replacement player. Given that, they [decided](https://fivethirtyeight.com/features/the-states-where-trump-is-more-and-less-popular-than-he-should-be/) to rate the president's approval versus each state's overall approval of his party (in recent elections), which is a way of rating the president's performance versus an average replacement candidate from the same party. I'll duplicate that work and keep it up to date.\n",
"\n",
"There are only four states where Trump is exceeding a replacement Republican (i.e., has a positive PARP): one deep-red southern state, Mississippi, and three deep-blue coastal states, Rhode Island, Hawaii, and Massachussetts. Again, the swing states are **bold CAPITALIZED**."
"There are only five states where Trump is exceeding a replacement Republican (i.e., has a positive PARP): one deep-red southern state, Mississippi, and four deep-blue coastal states, Hawaii, Delaware, Rhode Island, and Massachussetts. Again, the swing states are **BOLD CAPITALIZED**."
]
},
{
@@ -544,57 +540,57 @@
"text/markdown": [
"|State|PARP|Net|Lean|EV|\n",
"|-|-|-|-|-|\n",
"|Rhode Island|+6|-20|-26|4|\n",
"|Hawaii|+3|-33|-36|4|\n",
"|Hawaii|+13|-23|-36|4|\n",
"|Delaware|+5|-9|-14|3|\n",
"|Rhode Island|+5|-21|-26|4|\n",
"|Mississippi|+3|+18|+15|6|\n",
"|Massachusetts|+2|-27|-29|11|\n",
"|Mississippi|+2|+17|+15|6|\n",
"|Alabama|+0|+27|+27|9|\n",
"|Louisiana|+0|+17|+17|8|\n",
"|New York|+0|-22|-22|29|\n",
"|Delaware|-1|-15|-14|3|\n",
"|California|-4|-28|-24|55|\n",
"|Maine|-4|-9|-5|4|\n",
"|**FLORIDA**|-5|+0|+5|29|\n",
"|New Jersey|-5|-18|-13|14|\n",
"|Virginia|-6|-6|+0|13|\n",
"|New Jersey|-2|-15|-13|14|\n",
"|Alabama|-3|+24|+27|9|\n",
"|Louisiana|-3|+14|+17|8|\n",
"|New York|-3|-25|-22|29|\n",
"|Vermont|-4|-28|-24|3|\n",
"|**VIRGINIA**|-4|-4|+0|13|\n",
"|California|-5|-29|-24|55|\n",
"|Maryland|-5|-28|-23|10|\n",
"|Maine|-6|-11|-5|4|\n",
"|Illinois|-7|-20|-13|20|\n",
"|South Carolina|-7|+10|+17|9|\n",
"|Maryland|-8|-31|-23|10|\n",
"|New Mexico|-8|-15|-7|5|\n",
"|Pennsylvania|-8|-7|+1|20|\n",
"|Kentucky|-9|+14|+23|8|\n",
"|**NORTH CAROLINA**|-9|-4|+5|15|\n",
"|Vermont|-10|-34|-24|3|\n",
"|**GEORGIA**|-11|+1|+12|16|\n",
"|Michigan|-11|-12|-1|16|\n",
"|**OHIO**|-11|-4|+7|18|\n",
"|Nevada|-12|-11|+1|6|\n",
"|Tennessee|-12|+16|+28|11|\n",
"|West Virginia|-12|+18|+30|5|\n",
"|Colorado|-13|-14|-1|9|\n",
"|Connecticut|-13|-24|-11|7|\n",
"|**MISSOURI**|-13|+6|+19|10|\n",
"|Oregon|-13|-22|-9|7|\n",
"|**FLORIDA**|-8|-3|+5|29|\n",
"|Kentucky|-8|+15|+23|8|\n",
"|**NORTH CAROLINA**|-8|-3|+5|15|\n",
"|New Mexico|-9|-16|-7|5|\n",
"|South Carolina|-9|+8|+17|9|\n",
"|Oregon|-10|-19|-9|7|\n",
"|Pennsylvania|-10|-9|+1|20|\n",
"|**MONTANA**|-11|+7|+18|3|\n",
"|Nevada|-11|-10|+1|6|\n",
"|Tennessee|-11|+17|+28|11|\n",
"|West Virginia|-11|+19|+30|5|\n",
"|**ALASKA**|-12|+3|+15|3|\n",
"|Colorado|-12|-13|-1|9|\n",
"|Connecticut|-12|-23|-11|7|\n",
"|**GEORGIA**|-12|+0|+12|16|\n",
"|Ohio|-13|-6|+7|18|\n",
"|**TEXAS**|-13|+4|+17|38|\n",
"|Michigan|-14|-15|-1|16|\n",
"|Minnesota|-14|-16|-2|10|\n",
"|**TEXAS**|-14|+3|+17|38|\n",
"|Wisconsin|-14|-13|+1|10|\n",
"|**ALASKA**|-15|+0|+15|3|\n",
"|**ARIZONA**|-15|-6|+9|11|\n",
"|Idaho|-15|+20|+35|4|\n",
"|**INDIANA**|-15|+3|+18|11|\n",
"|**MONTANA**|-15|+3|+18|3|\n",
"|Arkansas|-16|+8|+24|6|\n",
"|Iowa|-18|-12|+6|6|\n",
"|Washington|-18|-30|-12|12|\n",
"|District of Columbia|-19|-62|-43|3|\n",
"|New Hampshire|-21|-19|+2|4|\n",
"|**KANSAS**|-22|+1|+23|6|\n",
"|**NEBRASKA**|-22|+2|+24|5|\n",
"|Oklahoma|-25|+9|+34|7|\n",
"|**SOUTH DAKOTA**|-25|+6|+31|3|\n",
"|Wisconsin|-15|-14|+1|10|\n",
"|**ARIZONA**|-16|-7|+9|11|\n",
"|District of Columbia|-16|-59|-43|3|\n",
"|Washington|-16|-28|-12|12|\n",
"|Idaho|-17|+18|+35|4|\n",
"|**INDIANA**|-17|+1|+18|11|\n",
"|**ARKANSAS**|-18|+6|+24|6|\n",
"|Iowa|-19|-13|+6|6|\n",
"|**MISSOURI**|-19|+0|+19|10|\n",
"|**KANSAS**|-20|+3|+23|6|\n",
"|Oklahoma|-22|+12|+34|7|\n",
"|**NEBRASKA**|-23|+1|+24|5|\n",
"|New Hampshire|-25|-23|+2|4|\n",
"|Wyoming|-25|+22|+47|3|\n",
"|**UTAH**|-29|+2|+31|6|\n",
"|**NORTH DAKOTA**|-32|+1|+33|3|"
"|**NORTH DAKOTA**|-27|+6|+33|3|\n",
"|**SOUTH DAKOTA**|-27|+4|+31|3|\n",
"|**UTAH**|-29|+2|+31|6|"
],
"text/plain": [
"<IPython.core.display.Markdown object>"