diff --git a/your-code/main.ipynb b/your-code/main.ipynb index cdc1acb..cd527ac 100644 --- a/your-code/main.ipynb +++ b/your-code/main.ipynb @@ -14,12 +14,13 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 34, "metadata": {}, "outputs": [], "source": [ "# import numpy and pandas\n", - "\n" + "import numpy as np\n", + "import pandas as pd\n" ] }, { @@ -35,7 +36,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 35, "metadata": {}, "outputs": [], "source": [ @@ -53,12 +54,334 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], + "execution_count": 36, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
#NameType 1Type 2TotalHPAttackDefenseSp. AtkSp. DefSpeedGenerationLegendary
01BulbasaurGrassPoison3184549496565451False
12IvysaurGrassPoison4056062638080601False
23VenusaurGrassPoison525808283100100801False
33VenusaurMega VenusaurGrassPoison62580100123122120801False
44CharmanderFireNaN3093952436050651False
55CharmeleonFireNaN4055864588065801False
66CharizardFireFlying534788478109851001False
76CharizardMega Charizard XFireDragon63478130111130851001False
86CharizardMega Charizard YFireFlying63478104781591151001False
97SquirtleWaterNaN3144448655064431False
108WartortleWaterNaN4055963806580581False
119BlastoiseWaterNaN530798310085105781False
129BlastoiseMega BlastoiseWaterNaN63079103120135115781False
1310CaterpieBugNaN1954530352020451False
1411MetapodBugNaN2055020552525301False
\n", + "
" + ], + "text/plain": [ + " # Name Type 1 Type 2 Total HP Attack Defense \\\n", + "0 1 Bulbasaur Grass Poison 318 45 49 49 \n", + "1 2 Ivysaur Grass Poison 405 60 62 63 \n", + "2 3 Venusaur Grass Poison 525 80 82 83 \n", + "3 3 VenusaurMega Venusaur Grass Poison 625 80 100 123 \n", + "4 4 Charmander Fire NaN 309 39 52 43 \n", + "5 5 Charmeleon Fire NaN 405 58 64 58 \n", + "6 6 Charizard Fire Flying 534 78 84 78 \n", + "7 6 CharizardMega Charizard X Fire Dragon 634 78 130 111 \n", + "8 6 CharizardMega Charizard Y Fire Flying 634 78 104 78 \n", + "9 7 Squirtle Water NaN 314 44 48 65 \n", + "10 8 Wartortle Water NaN 405 59 63 80 \n", + "11 9 Blastoise Water NaN 530 79 83 100 \n", + "12 9 BlastoiseMega Blastoise Water NaN 630 79 103 120 \n", + "13 10 Caterpie Bug NaN 195 45 30 35 \n", + "14 11 Metapod Bug NaN 205 50 20 55 \n", + "\n", + " Sp. Atk Sp. Def Speed Generation Legendary \n", + "0 65 65 45 1 False \n", + "1 80 80 60 1 False \n", + "2 100 100 80 1 False \n", + "3 122 120 80 1 False \n", + "4 60 50 65 1 False \n", + "5 80 65 80 1 False \n", + "6 109 85 100 1 False \n", + "7 130 85 100 1 False \n", + "8 159 115 100 1 False \n", + "9 50 64 43 1 False \n", + "10 65 80 58 1 False \n", + "11 85 105 78 1 False \n", + "12 135 115 78 1 False \n", + "13 20 20 45 1 False \n", + "14 25 25 30 1 False " + ] + }, + "execution_count": 36, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "# Your code here:\n", - "\n" + "pokemon.head(15)\n" ] }, { @@ -70,12 +393,29 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], + "execution_count": 37, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Legendary\n", + "False 735\n", + "True 65\n", + "Name: count, dtype: int64" + ] + }, + "execution_count": 37, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "# Your code here:\n", - "\n" + "\n", + "legendary_counts = pokemon['Legendary'].value_counts()\n", + "\n", + "legendary_counts" ] }, { @@ -87,12 +427,33 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], + "execution_count": 38, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "legendary_mean = 637.3846153846154\n", + "legendary_std = 60.93738905315344\n", + "non_legendary_mean = 417.21360544217686\n", + "non_legendary_std = 106.76041745713005\n" + ] + } + ], "source": [ "# Your code here:\n", - "\n" + "legendary_mean = pokemon[pokemon[\"Legendary\"] == True][\"Total\"].mean()\n", + "print(f\"legendary_mean = {legendary_mean}\")\n", + "\n", + "legendary_std = pokemon[pokemon[\"Legendary\"] == True][\"Total\"].std()\n", + "print(f\"legendary_std = {legendary_std}\")\n", + "\n", + "non_legendary_mean = pokemon[pokemon[\"Legendary\"] == False][\"Total\"].mean()\n", + "print(f\"non_legendary_mean = {non_legendary_mean}\")\n", + "\n", + "non_legendary_std = pokemon[pokemon[\"Legendary\"] == False][\"Total\"].std()\n", + "print(f\"non_legendary_std = {non_legendary_std}\")" ] }, { @@ -106,12 +467,107 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 39, "metadata": {}, "outputs": [], "source": [ "# Your code here:\n", - "\n" + "\n", + "# Null Hypothesis (H0): There is no significant difference in the mean total points between Legendary and Non-Legendary Pokémon.\n", + "# Alternative Hypothesis (H1): There is a significant difference in the mean total points between Legendary and Non-Legendary Pokémon.\n", + "\n", + "\n", + "from scipy.stats import ttest_ind\n", + "\n", + "# Separate Total points for Legendary and Non-Legendary\n", + "legendary_total = pokemon[pokemon[\"Legendary\"] == True][\"Total\"]\n", + "non_legendary_total = pokemon[pokemon[\"Legendary\"] == False][\"Total\"]\n" + ] + }, + { + "cell_type": "code", + "execution_count": 40, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "156 580\n", + "157 580\n", + "158 580\n", + "162 680\n", + "163 780\n", + " ... \n", + "795 600\n", + "796 700\n", + "797 600\n", + "798 680\n", + "799 600\n", + "Name: Total, Length: 65, dtype: int64" + ] + }, + "execution_count": 40, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "\n", + "legendary_total" + ] + }, + { + "cell_type": "code", + "execution_count": 56, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0 318\n", + "1 405\n", + "2 525\n", + "3 625\n", + "4 309\n", + " ... \n", + "787 494\n", + "788 304\n", + "789 514\n", + "790 245\n", + "791 535\n", + "Name: Total, Length: 735, dtype: int64" + ] + }, + "execution_count": 56, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "\n", + "non_legendary_total" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "T-statistic: 25.8335743895517\n", + "P-value: 9.357954335957444e-47\n" + ] + } + ], + "source": [ + "# T-test with unequal variances\n", + "t_stat, p_value = ttest_ind(legendary_total, non_legendary_total, equal_var=False)\n", + "\n", + "print(f\"T-statistic: {t_stat}\")\n", + "print(f\"P-value: {p_value}\") " ] }, { @@ -128,7 +584,8 @@ "outputs": [], "source": [ "# Your conclusions here:\n", - "\n" + "\n", + "# Reject the Null-Hypothesis: There is sufficient evidence to conclude that there is a significant difference in the mean total points between Legendary and Non-Legendary Pokémon.\n" ] }, { @@ -142,10 +599,43 @@ "cell_type": "code", "execution_count": null, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "Type 1\n", + "Water 112\n", + "Normal 98\n", + "Grass 70\n", + "Bug 69\n", + "Psychic 57\n", + "Fire 52\n", + "Electric 44\n", + "Rock 44\n", + "Dragon 32\n", + "Ground 32\n", + "Ghost 32\n", + "Dark 31\n", + "Poison 28\n", + "Steel 27\n", + "Fighting 27\n", + "Ice 24\n", + "Fairy 17\n", + "Flying 4\n", + "Name: count, dtype: int64" + ] + }, + "execution_count": 67, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "# Your code here:\n", - "\n" + "\n", + "type1_counts = pokemon[\"Type 1\"].value_counts()\n", + "\n", + "type1_counts\n" ] }, { @@ -157,12 +647,68 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], + "execution_count": 74, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "9 314\n", + "10 405\n", + "11 530\n", + "12 630\n", + "59 320\n", + " ... \n", + "724 314\n", + "725 405\n", + "726 530\n", + "762 330\n", + "763 500\n", + "Name: Total, Length: 112, dtype: int64" + ] + }, + "execution_count": 74, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "# Your code here:\n", - "\n" + "\n", + "water_pokemon_total = pokemon[pokemon[\"Type 1\"] == \"Water\"][\"Total\"]\n", + "non_water_pokemon_total = pokemon[pokemon[\"Type 1\"] != \"Water\"][\"Total\"]\n", + "\n", + "water_pokemon_total\n" + ] + }, + { + "cell_type": "code", + "execution_count": 77, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "water_total_mean = 430.45535714285717\n", + "water_total_std = 113.1882660643146\n", + "non_water_total_mean = 435.85901162790697\n", + "non_water_total_std = 121.0916823020807\n" + ] + } + ], + "source": [ + "water_total_mean = water_pokemon_total.mean()\n", + "print(f\"water_total_mean = {water_total_mean}\")\n", + "\n", + "water_total_std = water_pokemon_total.std()\n", + "print(f\"water_total_std = {water_total_std}\")\n", + "\n", + "non_water_total_mean = non_water_pokemon_total.mean()\n", + "print(f\"non_water_total_mean = {non_water_total_mean}\")\n", + "\n", + "non_water_total_std = non_water_pokemon_total.std()\n", + "print(f\"non_water_total_std = {non_water_total_std}\")" ] }, { @@ -174,12 +720,29 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], + "execution_count": 81, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "T-statistic: -0.4418547448849676\n", + "P-value: 0.6587140317488793\n" + ] + } + ], "source": [ "# Your code here:\n", - "\n" + "\n", + "# Null Hypothesis (H0): There is no significant difference in the mean total points between Water-type Pokémon and Non-Water Pokémon.\n", + "# Alternative Hypothesis (H1): There is a significant difference in the mean total points.\n", + "\n", + "\n", + "t_stat, p_value = ttest_ind(water_pokemon_total, non_water_pokemon_total, equal_var=True)\n", + "\n", + "print(f\"T-statistic: {t_stat}\")\n", + "print(f\"P-value: {p_value}\") # Scientific notation for small values" ] }, { @@ -196,6 +759,8 @@ "outputs": [], "source": [ "# Your conclusions here:\n", + "\n", + "# Fail to reject Null Hypothesis: Not enough evidence to say there is a significant difference in the mean total points.\n", "\n" ] }, @@ -212,10 +777,31 @@ "cell_type": "code", "execution_count": null, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "T-statistic: -4.325566393330478\n", + "P-value: 1.7140303479358558e-05\n" + ] + } + ], "source": [ "# Your code here:\n", - "\n" + "\n", + "# Null Hypothesis (H0): The defense and attack scores of each Pokemon are equal.\n", + "# Alternative Hypothesis (H1): The defense and attack scores of each Pokemon are NOT equal.\n", + "\n", + "# MY NOTE: Paired (dependant) t-test is needed because we are dealing with paired observations (each Pokémon has both an Attack and Defense score).\n", + "\n", + "from scipy.stats import ttest_rel\n", + "\n", + "t_stat, p_value = ttest_rel(pokemon[\"Defense\"], pokemon[\"Attack\"])\n", + "\n", + "\n", + "print(f\"T-statistic: {t_stat}\")\n", + "print(f\"P-value: {p_value}\") " ] }, { @@ -232,7 +818,8 @@ "outputs": [], "source": [ "# Your conclusions here:\n", - "\n" + "\n", + "# Reject the Null Hypothesis: There is significant statistical evidence that the Defense and Attack scores of Pokémon are not equal." ] }, { @@ -246,10 +833,28 @@ "cell_type": "code", "execution_count": null, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "T-statistic: 0.853986188453353\n", + "P-value: 0.3933685997548122\n" + ] + } + ], "source": [ "# Your code here:\n", - "\n" + "\n", + "# Null Hypothesis (H0): The mean Special Attack and Special Defense scores are equal.\n", + "# Alternative Hypothesis (H1): The mean Special Attack and Special Defense scores are NOT equal.\n", + "\n", + "# MY NOTE: Paired (dependant) t-test is needed because we are dealing with paired observations.\n", + "\n", + "t_stat, p_value = ttest_rel(pokemon[\"Sp. Atk\"], pokemon[\"Sp. Def\"])\n", + "\n", + "print(f\"T-statistic: {t_stat}\")\n", + "print(f\"P-value: {p_value}\") \n" ] }, { @@ -266,7 +871,8 @@ "outputs": [], "source": [ "# Your conclusions here:\n", - "\n" + "\n", + "# Failed to reject Null Hypothesis: There is not enough evidence to state that mean Special Attack and Special Defense scores are NOT equal.\n" ] }, { @@ -282,10 +888,31 @@ "cell_type": "code", "execution_count": null, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "T-statistic: -0.853986188453353\n", + "P-value: 0.3933685997548122\n" + ] + } + ], "source": [ "# Your code here:\n", " \n", + "from scipy.stats import ttest_1samp\n", + "\n", + "differences = pokemon[\"Sp. Def\"] - pokemon[\"Sp. Atk\"]\n", + "\n", + "# one-sample t-test on the differences\n", + "t_stat, p_value = ttest_1samp(differences, 0) # Testing if the mean difference is 0\n", + "\n", + "\n", + "print(f\"T-statistic: {t_stat}\")\n", + "print(f\"P-value: {p_value}\")\n", + "\n", + "# Same result!\n", " " ] }, @@ -302,7 +929,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 53, "metadata": {}, "outputs": [], "source": [ @@ -319,7 +946,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 54, "metadata": {}, "outputs": [], "source": [ @@ -336,7 +963,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 55, "metadata": {}, "outputs": [], "source": [ @@ -368,7 +995,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.9" + "version": "3.11.1" } }, "nbformat": 4,