andre/100-Days-Of-ML-Code
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #99 from yx-xyc/mybranch

Browse Source 
Mybranch
This commit is contained in:
Yong Mao
2021-01-18 19:50:01 +08:00
committed by GitHub
parent 6fa241536f ce611639a5
commit a592ea0c37
4 changed files with 385 additions and 409 deletions
Download Patch File Download Diff File Expand all files Collapse all files

243
Code/Day 1_Data_Preprocessing.ipynb
View File

@ -19,7 +19,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 42,
"metadata": {},
"outputs": [],
"source": [
@ -27,6 +27,63 @@
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"[[ 7. 2. 3. ]\n [ 4. 3.5 6. ]\n [10. 3.5 9. ]]\nSklearn verion is 0.23.1\n"
]
}
],
"source": [
"import sklearn\n",
"from sklearn.impute import SimpleImputer\n",
"#This block is an example used to learn SimpleImputer\n",
"imp_mean = SimpleImputer(missing_values=np.nan, strategy='mean')\n",
"imp_mean.fit([[7, 2, 3], [4, np.nan, 6], [10, 5, 9]])\n",
"X = [[np.nan, 2, 3], [4, np.nan, 6], [10, np.nan, 9]]\n",
"print(imp_mean.transform(X))\n",
"print(\"Sklearn verion is {}\".format(sklearn.__version__))"
]
},
{
"source": [
"from sklearn.preprocessing import OneHotEncoder\n",
"enc = OneHotEncoder(handle_unknown='ignore')\n",
"X = [['Male', 1], ['Female', 3], ['Female', 2]]\n",
">>> enc.fit(X)\n",
"OneHotEncoder(handle_unknown='ignore')\n",
">>> enc.categories_\n",
"[array(['Female', 'Male'], dtype=object), array([1, 2, 3], dtype=object)]\n",
">>> enc.transform([['Female', 1], ['Male', 4]]).toarray()\n",
"array([[1., 0., 1., 0., 0.],\n",
" [0., 1., 0., 0., 0.]])\n",
">>> enc.inverse_transform([[0, 1, 1, 0, 0], [0, 0, 0, 1, 0]])\n",
"array([['Male', 1],\n",
" [None, 2]], dtype=object)\n",
">>> enc.get_feature_names(['gender', 'group'])\n",
"array(['gender_Female', 'gender_Male', 'group_1', 'group_2', 'group_3'],\n",
" dtype=object)"
],
"cell_type": "code",
"metadata": {},
"execution_count": 4,
"outputs": [
{
"output_type": "error",
"ename": "SyntaxError",
"evalue": "invalid syntax (<ipython-input-4-44f585aeb41d>, line 4)",
"traceback": [
"\u001b[1;36m File \u001b[1;32m\"<ipython-input-4-44f585aeb41d>\"\u001b[1;36m, line \u001b[1;32m4\u001b[0m\n\u001b[1;33m >>> enc.fit(X)\u001b[0m\n\u001b[1;37m ^\u001b[0m\n\u001b[1;31mSyntaxError\u001b[0m\u001b[1;31m:\u001b[0m invalid syntax\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {},
@ -37,27 +94,14 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 52,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"name": "stdout",
"text": [
"Step 2: Importing dataset\n",
"X\n",
"[['France' 44.0 72000.0]\n",
" ['Spain' 27.0 48000.0]\n",
" ['Germany' 30.0 54000.0]\n",
" ['Spain' 38.0 61000.0]\n",
" ['Germany' 40.0 nan]\n",
" ['France' 35.0 58000.0]\n",
" ['Spain' nan 52000.0]\n",
" ['France' 48.0 79000.0]\n",
" ['Germany' 50.0 83000.0]\n",
" ['France' 37.0 67000.0]]\n",
"Y\n",
"['No' 'Yes' 'No' 'No' 'Yes' 'Yes' 'No' 'Yes' 'No' 'Yes']\n"
"Step 2: Importing dataset\nX\n[['France' 44.0 72000.0]\n ['Spain' 27.0 48000.0]\n ['Germany' 30.0 54000.0]\n ['Spain' 38.0 61000.0]\n ['Germany' 40.0 nan]\n ['France' 35.0 58000.0]\n ['Spain' nan 52000.0]\n ['France' 48.0 79000.0]\n ['Germany' 50.0 83000.0]\n ['France' 37.0 67000.0]]\nY\n['No' 'Yes' 'No' 'No' 'Yes' 'Yes' 'No' 'Yes' 'No' 'Yes']\n[[44.0 72000.0]\n [27.0 48000.0]\n [30.0 54000.0]\n [38.0 61000.0]\n [40.0 nan]\n [35.0 58000.0]\n [nan 52000.0]\n [48.0 79000.0]\n [50.0 83000.0]\n [37.0 67000.0]]\n"
]
}
],
@ -71,7 +115,8 @@
"print(\"X\")\n",
"print(X)\n",
"print(\"Y\")\n",
"print(Y)"
"print(Y)\n",
"print(X[ : , 1:3])"
]
},
{
@ -84,39 +129,31 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 53,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"name": "stdout",
"text": [
"---------------------\n",
"Step 3: Handling the missing data\n",
"step2\n",
"X\n",
"[['France' 44.0 72000.0]\n",
" ['Spain' 27.0 48000.0]\n",
" ['Germany' 30.0 54000.0]\n",
" ['Spain' 38.0 61000.0]\n",
" ['Germany' 40.0 63777.77777777778]\n",
" ['France' 35.0 58000.0]\n",
" ['Spain' 38.77777777777778 52000.0]\n",
" ['France' 48.0 79000.0]\n",
" ['Germany' 50.0 83000.0]\n",
" ['France' 37.0 67000.0]]\n"
"---------------------\nStep 3: Handling the missing data\nstep2\nX\n[['France' 44.0 72000.0]\n ['Spain' 27.0 48000.0]\n ['Germany' 30.0 54000.0]\n ['Spain' 38.0 61000.0]\n ['Germany' 40.0 63777.77777777778]\n ['France' 35.0 58000.0]\n ['Spain' 38.77777777777778 52000.0]\n ['France' 48.0 79000.0]\n ['Germany' 50.0 83000.0]\n ['France' 37.0 67000.0]]\n"
]
}
],
"source": [
"# If you use the newest version of sklearn, use the lines of code commented out",
"# from sklearn.impute import SimpleImputer",
"# imputer = SimpleImputer(missing_values=\"NaN\", strategy=\"mean\")",
"from sklearn.preprocessing import Imputer\n",
"# If you use the newest version of sklearn, use the lines of code commented out\n",
"from sklearn.impute import SimpleImputer\n",
"imputer = SimpleImputer(missing_values=np.nan, strategy=\"mean\")\n",
"#from sklearn.preprocessing import Imputer\n",
"# axis=0表示按列进行\n",
"imputer = Imputer(missing_values = \"NaN\", strategy = \"mean\", axis = 0)\n",
"imputer = imputer.fit(X[ : , 1:3])\n",
"X[ : , 1:3] = imputer.transform(X[ : , 1:3])\n",
"#imputer = Imputer(missing_values = \"NaN\", strategy = \"mean\", axis = 0)\n",
"#print(imputer)\n",
"#\n",
"# print(X[ : , 1:3])\n",
"imputer = imputer.fit(X[ : , 1:3]) #put the data we want to process in to this imputer\n",
"X[ : , 1:3] = imputer.transform(X[ : , 1:3]) #replace the np.nan with mean\n",
"#print(X[ : , 1:3])\n",
"print(\"---------------------\")\n",
"print(\"Step 3: Handling the missing data\")\n",
"print(\"step2\")\n",
@ -134,48 +171,30 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 54,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"name": "stdout",
"text": [
"---------------------\n",
"Step 4: Encoding categorical data\n",
"X\n",
"[[1.00000000e+00 0.00000000e+00 0.00000000e+00 4.40000000e+01\n",
" 7.20000000e+04]\n",
" [0.00000000e+00 0.00000000e+00 1.00000000e+00 2.70000000e+01\n",
" 4.80000000e+04]\n",
" [0.00000000e+00 1.00000000e+00 0.00000000e+00 3.00000000e+01\n",
" 5.40000000e+04]\n",
" [0.00000000e+00 0.00000000e+00 1.00000000e+00 3.80000000e+01\n",
" 6.10000000e+04]\n",
" [0.00000000e+00 1.00000000e+00 0.00000000e+00 4.00000000e+01\n",
" 6.37777778e+04]\n",
" [1.00000000e+00 0.00000000e+00 0.00000000e+00 3.50000000e+01\n",
" 5.80000000e+04]\n",
" [0.00000000e+00 0.00000000e+00 1.00000000e+00 3.87777778e+01\n",
" 5.20000000e+04]\n",
" [1.00000000e+00 0.00000000e+00 0.00000000e+00 4.80000000e+01\n",
" 7.90000000e+04]\n",
" [0.00000000e+00 1.00000000e+00 0.00000000e+00 5.00000000e+01\n",
" 8.30000000e+04]\n",
" [1.00000000e+00 0.00000000e+00 0.00000000e+00 3.70000000e+01\n",
" 6.70000000e+04]]\n",
"Y\n",
"[0 1 0 0 1 1 0 1 0 1]\n"
"---------------------\nStep 4: Encoding categorical data\nX\n[[1.0 0.0 0.0 44.0 72000.0]\n [0.0 0.0 1.0 27.0 48000.0]\n [0.0 1.0 0.0 30.0 54000.0]\n [0.0 0.0 1.0 38.0 61000.0]\n [0.0 1.0 0.0 40.0 63777.77777777778]\n [1.0 0.0 0.0 35.0 58000.0]\n [0.0 0.0 1.0 38.77777777777778 52000.0]\n [1.0 0.0 0.0 48.0 79000.0]\n [0.0 1.0 0.0 50.0 83000.0]\n [1.0 0.0 0.0 37.0 67000.0]]\nY\n[0 1 0 0 1 1 0 1 0 1]\n"
]
}
],
"source": [
"from sklearn.preprocessing import LabelEncoder, OneHotEncoder\n",
"labelencoder_X = LabelEncoder()\n",
"X[ : , 0] = labelencoder_X.fit_transform(X[ : , 0])\n",
"from sklearn.compose import ColumnTransformer \n",
"#labelencoder_X = LabelEncoder()\n",
"#X[ : , 0] = labelencoder_X.fit_transform(X[ : , 0])\n",
"#Creating a dummy variable\n",
"onehotencoder = OneHotEncoder(categorical_features = [0])\n",
"X = onehotencoder.fit_transform(X).toarray()\n",
"#print(X)\n",
"ct = ColumnTransformer([(\"\", OneHotEncoder(), [0])], remainder = 'passthrough')\n",
"X = ct.fit_transform(X)\n",
"#onehotencoder = OneHotEncoder(categorical_features = [0])\n",
"#X = onehotencoder.fit_transform(X).toarray()\n",
"labelencoder_Y = LabelEncoder()\n",
"Y = labelencoder_Y.fit_transform(Y)\n",
"print(\"---------------------\")\n",
@ -196,41 +215,14 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 55,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"name": "stdout",
"text": [
"---------------------\n",
"Step 5: Splitting the datasets into training sets and Test sets\n",
"X_train\n",
"[[ 0.00000000e+00 1.00000000e+00 0.00000000e+00 4.00000000e+01\n",
" 6.37777778e+04]\n",
" [ 1.00000000e+00 0.00000000e+00 0.00000000e+00 3.70000000e+01\n",
" 6.70000000e+04]\n",
" [ 0.00000000e+00 0.00000000e+00 1.00000000e+00 2.70000000e+01\n",
" 4.80000000e+04]\n",
" [ 0.00000000e+00 0.00000000e+00 1.00000000e+00 3.87777778e+01\n",
" 5.20000000e+04]\n",
" [ 1.00000000e+00 0.00000000e+00 0.00000000e+00 4.80000000e+01\n",
" 7.90000000e+04]\n",
" [ 0.00000000e+00 0.00000000e+00 1.00000000e+00 3.80000000e+01\n",
" 6.10000000e+04]\n",
" [ 1.00000000e+00 0.00000000e+00 0.00000000e+00 4.40000000e+01\n",
" 7.20000000e+04]\n",
" [ 1.00000000e+00 0.00000000e+00 0.00000000e+00 3.50000000e+01\n",
" 5.80000000e+04]]\n",
"X_test\n",
"[[ 0.00000000e+00 1.00000000e+00 0.00000000e+00 3.00000000e+01\n",
" 5.40000000e+04]\n",
" [ 0.00000000e+00 1.00000000e+00 0.00000000e+00 5.00000000e+01\n",
" 8.30000000e+04]]\n",
"Y_train\n",
"[1 1 1 0 1 0 0 1]\n",
"Y_test\n",
"[0 0]\n"
"---------------------\nStep 5: Splitting the datasets into training sets and Test sets\nX_train\n[[0.0 1.0 0.0 40.0 63777.77777777778]\n [1.0 0.0 0.0 37.0 67000.0]\n [0.0 0.0 1.0 27.0 48000.0]\n [0.0 0.0 1.0 38.77777777777778 52000.0]\n [1.0 0.0 0.0 48.0 79000.0]\n [0.0 0.0 1.0 38.0 61000.0]\n [1.0 0.0 0.0 44.0 72000.0]\n [1.0 0.0 0.0 35.0 58000.0]]\nX_test\n[[0.0 1.0 0.0 30.0 54000.0]\n [0.0 1.0 0.0 50.0 83000.0]]\nY_train\n[1 1 1 0 1 0 0 1]\nY_test\n[0 0]\n"
]
}
],
@ -259,27 +251,15 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 57,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"name": "stdout",
"text": [
"---------------------\n",
"Step 6: Feature Scaling\n",
"X_train\n",
"[[-1. 2.64575131 -0.77459667 0.26306757 0.12381479]\n",
" [ 1. -0.37796447 -0.77459667 -0.25350148 0.46175632]\n",
" [-1. -0.37796447 1.29099445 -1.97539832 -1.53093341]\n",
" [-1. -0.37796447 1.29099445 0.05261351 -1.11141978]\n",
" [ 1. -0.37796447 -0.77459667 1.64058505 1.7202972 ]\n",
" [-1. -0.37796447 1.29099445 -0.0813118 -0.16751412]\n",
" [ 1. -0.37796447 -0.77459667 0.95182631 0.98614835]\n",
" [ 1. -0.37796447 -0.77459667 -0.59788085 -0.48214934]]\n",
"X_test\n",
"[[ 0. 0. 0. -1. -1.]\n",
" [ 0. 0. 0. 1. 1.]]\n"
"---------------------\nStep 6: Feature Scaling\nX_train\n[[-1. 2.64575131 -0.77459667 0.26306757 0.12381479]\n [ 1. -0.37796447 -0.77459667 -0.25350148 0.46175632]\n [-1. -0.37796447 1.29099445 -1.97539832 -1.53093341]\n [-1. -0.37796447 1.29099445 0.05261351 -1.11141978]\n [ 1. -0.37796447 -0.77459667 1.64058505 1.7202972 ]\n [-1. -0.37796447 1.29099445 -0.0813118 -0.16751412]\n [ 1. -0.37796447 -0.77459667 0.95182631 0.98614835]\n [ 1. -0.37796447 -0.77459667 -0.59788085 -0.48214934]]\nX_test\n[[-1. 2.64575131 -0.77459667 -1.45882927 -0.90166297]\n [-1. 2.64575131 -0.77459667 1.98496442 2.13981082]]\n"
]
}
],
@ -287,13 +267,13 @@
"from sklearn.preprocessing import StandardScaler\n",
"sc_X = StandardScaler()\n",
"X_train = sc_X.fit_transform(X_train)\n",
"X_test = sc_X.transform(X_test)\n",
"X_test = sc_X.transform(X_test) #we should not use fit_transfer cause the u and z is determined from x_train\n",
"print(\"---------------------\")\n",
"print(\"Step 6: Feature Scaling\")\n",
"print(\"X_train\")\n",
"print(X_train)\n",
"print(\"X_test\")\n",
"print(X_test)"
"print(X_test)\n"
]
},
{
@ -302,22 +282,17 @@
"source": [
"<b>完整的项目请前往Github项目<a href=\"https://github.com/MachineLearning100/100-Days-Of-ML-Code\">100-Days-Of-ML-Code</a>查看。有任何的建议或者意见欢迎在issue中提出~</b>"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
"name": "python3",
"display_name": "Python 3.8.3 64-bit (conda)",
"metadata": {
"interpreter": {
"hash": "1b78ff499ec469310b6a6795c4effbbfc85eb20a6ba0cf828a15721670711b2c"
}
}
},
"language_info": {
"codemirror_mode": {
@ -329,9 +304,9 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.5"
"version": "3.8.3-final"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
}

147
Code/Day 1_Data_Preprocessing.py
View File

@ -1,71 +1,76 @@
#Day 1: Data Prepocessing
#Step 1: Importing the libraries
import numpy as np
import pandas as pd
#Step 2: Importing dataset
dataset = pd.read_csv('../datasets/Data.csv')
X = dataset.iloc[ : , :-1].values
Y = dataset.iloc[ : , 3].values
print("Step 2: Importing dataset")
print("X")
print(X)
print("Y")
print(Y)
#Step 3: Handling the missing data
# If you use the newest version of sklearn, use the lines of code commented out
# from sklearn.impute import SimpleImputer
# imputer = SimpleImputer(missing_values=np.nan, strategy="mean")
from sklearn.preprocessing import Imputer
imputer = Imputer(missing_values = "NaN", strategy = "mean", axis = 0)
imputer = imputer.fit(X[ : , 1:3])
X[ : , 1:3] = imputer.transform(X[ : , 1:3])
print("---------------------")
print("Step 3: Handling the missing data")
print("step2")
print("X")
print(X)
#Step 4: Encoding categorical data
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X = LabelEncoder()
X[ : , 0] = labelencoder_X.fit_transform(X[ : , 0])
#Creating a dummy variable
onehotencoder = OneHotEncoder(categorical_features = [0])
X = onehotencoder.fit_transform(X).toarray()
labelencoder_Y = LabelEncoder()
Y = labelencoder_Y.fit_transform(Y)
print("---------------------")
print("Step 4: Encoding categorical data")
print("X")
print(X)
print("Y")
print(Y)
#Step 5: Splitting the datasets into training sets and Test sets
from sklearn.model_selection import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split( X , Y , test_size = 0.2, random_state = 0)
print("---------------------")
print("Step 5: Splitting the datasets into training sets and Test sets")
print("X_train")
print(X_train)
print("X_test")
print(X_test)
print("Y_train")
print(Y_train)
print("Y_test")
print(Y_test)
#Step 6: Feature Scaling
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)
print("---------------------")
print("Step 6: Feature Scaling")
print("X_train")
print(X_train)
print("X_test")
print(X_test)
#Day 1: Data Prepocessing
#Step 1: Importing the libraries
import numpy as np
import pandas as pd
#Step 2: Importing dataset
dataset = pd.read_csv('../datasets/Data.csv')
X = dataset.iloc[ : , :-1].values
Y = dataset.iloc[ : , 3].values
print("Step 2: Importing dataset")
print("X")
print(X)
print("Y")
print(Y)
#Step 3: Handling the missing data
# If you use the newest version of sklearn, use the lines of code commented out
from sklearn.impute import SimpleImputer
imputer = SimpleImputer(missing_values=np.nan, strategy="mean")
#from sklearn.preprocessing import Imputer
# axis=0表示按列进行
#imputer = Imputer(missing_values = "NaN", strategy = "mean", axis = 0)
imputer = imputer.fit(X[ : , 1:3])
X[ : , 1:3] = imputer.transform(X[ : , 1:3])
print("---------------------")
print("Step 3: Handling the missing data")
print("step2")
print("X")
print(X)
#Step 4: Encoding categorical data
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
from sklearn.compose import ColumnTransformer
#labelencoder_X = LabelEncoder()
#X[ : , 0] = labelencoder_X.fit_transform(X[ : , 0])
#Creating a dummy variable
#print(X)
ct = ColumnTransformer([("", OneHotEncoder(), [0])], remainder = 'passthrough')
X = ct.fit_transform(X)
#onehotencoder = OneHotEncoder(categorical_features = [0])
#X = onehotencoder.fit_transform(X).toarray()
labelencoder_Y = LabelEncoder()
Y = labelencoder_Y.fit_transform(Y)
print("---------------------")
print("Step 4: Encoding categorical data")
print("X")
print(X)
print("Y")
print(Y)
#Step 5: Splitting the datasets into training sets and Test sets
from sklearn.model_selection import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split( X , Y , test_size = 0.2, random_state = 0)
print("---------------------")
print("Step 5: Splitting the datasets into training sets and Test sets")
print("X_train")
print(X_train)
print("X_test")
print(X_test)
print("Y_train")
print(Y_train)
print("Y_test")
print(Y_test)
#Step 6: Feature Scaling
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)
print("---------------------")
print("Step 6: Feature Scaling")
print("X_train")
print(X_train)
print("X_test")
print(X_test)

197
Code/Day 2_Simple_Linear_Regression.ipynb
View File

File diff suppressed because one or more lines are too long

207
Code/Day 3_Multiple_Linear_Regression.ipynb
View File

@ -23,7 +23,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 45,
"metadata": {},
"outputs": [],
"source": [
@ -40,40 +40,64 @@
},
{
"cell_type": "code",
"execution_count": 30,
"execution_count": 57,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"name": "stdout",
"text": [
"[[165349.2 136897.8 471784.1 'New York']\n",
" [162597.7 151377.59 443898.53 'California']\n",
" [153441.51 101145.55 407934.54 'Florida']\n",
" [144372.41 118671.85 383199.62 'New York']\n",
" [142107.34 91391.77 366168.42 'Florida']\n",
" [131876.9 99814.71 362861.36 'New York']\n",
" [134615.46 147198.87 127716.82 'California']\n",
" [130298.13 145530.06 323876.68 'Florida']\n",
" [120542.52 148718.95 311613.29 'New York']\n",
" [123334.88 108679.17 304981.62 'California']]\n",
"[192261.83 191792.06 191050.39 182901.99 166187.94 156991.12 156122.51\n",
" 155752.6 152211.77 149759.96 146121.95 144259.4 141585.52 134307.35\n",
" 132602.65 129917.04 126992.93 125370.37 124266.9 122776.86 118474.03\n",
" 111313.02 110352.25 108733.99 108552.04 107404.34 105733.54 105008.31\n",
" 103282.38 101004.64 99937.59 97483.56 97427.84 96778.92 96712.8\n",
" 96479.51 90708.19 89949.14 81229.06 81005.76 78239.91 77798.83\n",
" 71498.49 69758.98 65200.33 64926.08 49490.75 42559.73 35673.41\n",
" 14681.4 ]\n"
"X:\n[[165349.2 136897.8 471784.1 'New York']\n [162597.7 151377.59 443898.53 'California']\n [153441.51 101145.55 407934.54 'Florida']\n [144372.41 118671.85 383199.62 'New York']\n [142107.34 91391.77 366168.42 'Florida']\n [131876.9 99814.71 362861.36 'New York']\n [134615.46 147198.87 127716.82 'California']\n [130298.13 145530.06 323876.68 'Florida']\n [120542.52 148718.95 311613.29 'New York']\n [123334.88 108679.17 304981.62 'California']]\nY:\n[192261.83 191792.06 191050.39 182901.99 166187.94 156991.12 156122.51\n 155752.6 152211.77 149759.96 146121.95 144259.4 141585.52 134307.35\n 132602.65 129917.04 126992.93 125370.37 124266.9 122776.86 118474.03\n 111313.02 110352.25 108733.99 108552.04 107404.34 105733.54 105008.31\n 103282.38 101004.64 99937.59 97483.56 97427.84 96778.92 96712.8\n 96479.51 90708.19 89949.14 81229.06 81005.76 78239.91 77798.83\n 71498.49 69758.98 65200.33 64926.08 49490.75 42559.73 35673.41\n 14681.4 ]\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
" R&D Spend Administration Marketing Spend State Profit\n",
"0 165349.20 136897.80 471784.10 New York 192261.83\n",
"1 162597.70 151377.59 443898.53 California 191792.06\n",
"2 153441.51 101145.55 407934.54 Florida 191050.39\n",
"3 144372.41 118671.85 383199.62 New York 182901.99\n",
"4 142107.34 91391.77 366168.42 Florida 166187.94"
],
"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>R&amp;D Spend</th>\n <th>Administration</th>\n <th>Marketing Spend</th>\n <th>State</th>\n <th>Profit</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>165349.20</td>\n <td>136897.80</td>\n <td>471784.10</td>\n <td>New York</td>\n <td>192261.83</td>\n </tr>\n <tr>\n <th>1</th>\n <td>162597.70</td>\n <td>151377.59</td>\n <td>443898.53</td>\n <td>California</td>\n <td>191792.06</td>\n </tr>\n <tr>\n <th>2</th>\n <td>153441.51</td>\n <td>101145.55</td>\n <td>407934.54</td>\n <td>Florida</td>\n <td>191050.39</td>\n </tr>\n <tr>\n <th>3</th>\n <td>144372.41</td>\n <td>118671.85</td>\n <td>383199.62</td>\n <td>New York</td>\n <td>182901.99</td>\n </tr>\n <tr>\n <th>4</th>\n <td>142107.34</td>\n <td>91391.77</td>\n <td>366168.42</td>\n <td>Florida</td>\n <td>166187.94</td>\n </tr>\n </tbody>\n</table>\n</div>"
},
"metadata": {},
"execution_count": 57
}
],
"source": [
"dataset = pd.read_csv('../datasets/50_Startups.csv')\n",
"X = dataset.iloc[ : , :-1].values\n",
"Y = dataset.iloc[ : , 4 ].values\n",
"Z = dataset.iloc[ : , 0 ].values\n",
"print(\"X:\")\n",
"print(X[:10])\n",
"print(Y)"
"print(\"Y:\")\n",
"print(Y)\n",
"dataset.head(5)"
]
},
{
"cell_type": "code",
"execution_count": 59,
"metadata": {},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"[[165349.2 136897.8 471784.1 'New York']\n [162597.7 151377.59 443898.53 'California']\n [153441.51 101145.55 407934.54 'Florida']\n [144372.41 118671.85 383199.62 'New York']\n [142107.34 91391.77 366168.42 'Florida']\n [131876.9 99814.71 362861.36 'New York']\n [134615.46 147198.87 127716.82 'California']\n [130298.13 145530.06 323876.68 'Florida']\n [120542.52 148718.95 311613.29 'New York']\n [123334.88 108679.17 304981.62 'California']\n [101913.08 110594.11 229160.95 'Florida']\n [100671.96 91790.61 249744.55 'California']\n [93863.75 127320.38 249839.44 'Florida']\n [91992.39 135495.07 252664.93 'California']\n [119943.24 156547.42 256512.92 'Florida']\n [114523.61 122616.84 261776.23 'New York']\n [78013.11 121597.55 264346.06 'California']\n [94657.16 145077.58 282574.31 'New York']\n [91749.16 114175.79 294919.57 'Florida']\n [86419.7 153514.11 224494.78489361703 'New York']\n [76253.86 113867.3 298664.47 'California']\n [78389.47 153773.43 299737.29 'New York']\n [73994.56 122782.75 303319.26 'Florida']\n [67532.53 105751.03 304768.73 'Florida']\n [77044.01 99281.34 140574.81 'New York']\n [64664.71 139553.16 137962.62 'California']\n [75328.87 144135.98 134050.07 'Florida']\n [72107.6 127864.55 353183.81 'New York']\n [66051.52 182645.56 118148.2 'Florida']\n [65605.48 153032.06 107138.38 'New York']\n [61994.48 115641.28 91131.24 'Florida']\n [61136.38 152701.92 88218.23 'New York']\n [63408.86 129219.61 46085.25 'California']\n [55493.95 103057.49 214634.81 'Florida']\n [46426.07 157693.92 210797.67 'California']\n [46014.02 85047.44 205517.64 'New York']\n [28663.76 127056.21 201126.82 'Florida']\n [44069.95 51283.14 197029.42 'California']\n [20229.59 65947.93 185265.1 'New York']\n [38558.51 82982.09 174999.3 'California']\n [28754.33 118546.05 172795.67 'California']\n [27892.92 84710.77 164470.71 'Florida']\n [23640.93 96189.63 148001.11 'California']\n [15505.73 127382.3 35534.17 'New York']\n [22177.74 154806.14 28334.72 'California']\n [1000.23 124153.04 1903.93 'New York']\n [1315.46 115816.21 297114.46 'Florida']\n [76793.34958333334 135426.92 224494.78489361703 'California']\n [542.05 51743.15 224494.78489361703 'New York']\n [76793.34958333334 116983.8 45173.06 'California']]\n"
]
}
],
"source": [
"from sklearn.impute import SimpleImputer\n",
"imputer = SimpleImputer(missing_values=0.0, strategy=\"mean\")\n",
"imputer = imputer.fit(X[ : , 0:3])\n",
"X[ : , 0:3] = imputer.transform(X[ : , 0:3])\n",
"print(X)"
]
},
{
@ -85,56 +109,32 @@
},
{
"cell_type": "code",
"execution_count": 31,
"execution_count": 60,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"name": "stdout",
"text": [
"labelencoder:\n",
"[[165349.2 136897.8 471784.1 2]\n",
" [162597.7 151377.59 443898.53 0]\n",
" [153441.51 101145.55 407934.54 1]\n",
" [144372.41 118671.85 383199.62 2]\n",
" [142107.34 91391.77 366168.42 1]\n",
" [131876.9 99814.71 362861.36 2]\n",
" [134615.46 147198.87 127716.82 0]\n",
" [130298.13 145530.06 323876.68 1]\n",
" [120542.52 148718.95 311613.29 2]\n",
" [123334.88 108679.17 304981.62 0]]\n",
"onehot:\n",
"[[0.0000000e+00 0.0000000e+00 1.0000000e+00 1.6534920e+05 1.3689780e+05\n",
" 4.7178410e+05]\n",
" [1.0000000e+00 0.0000000e+00 0.0000000e+00 1.6259770e+05 1.5137759e+05\n",
" 4.4389853e+05]\n",
" [0.0000000e+00 1.0000000e+00 0.0000000e+00 1.5344151e+05 1.0114555e+05\n",
" 4.0793454e+05]\n",
" [0.0000000e+00 0.0000000e+00 1.0000000e+00 1.4437241e+05 1.1867185e+05\n",
" 3.8319962e+05]\n",
" [0.0000000e+00 1.0000000e+00 0.0000000e+00 1.4210734e+05 9.1391770e+04\n",
" 3.6616842e+05]\n",
" [0.0000000e+00 0.0000000e+00 1.0000000e+00 1.3187690e+05 9.9814710e+04\n",
" 3.6286136e+05]\n",
" [1.0000000e+00 0.0000000e+00 0.0000000e+00 1.3461546e+05 1.4719887e+05\n",
" 1.2771682e+05]\n",
" [0.0000000e+00 1.0000000e+00 0.0000000e+00 1.3029813e+05 1.4553006e+05\n",
" 3.2387668e+05]\n",
" [0.0000000e+00 0.0000000e+00 1.0000000e+00 1.2054252e+05 1.4871895e+05\n",
" 3.1161329e+05]\n",
" [1.0000000e+00 0.0000000e+00 0.0000000e+00 1.2333488e+05 1.0867917e+05\n",
" 3.0498162e+05]]\n"
"original:\n[[165349.2 136897.8 471784.1 'New York']\n [162597.7 151377.59 443898.53 'California']\n [153441.51 101145.55 407934.54 'Florida']\n [144372.41 118671.85 383199.62 'New York']\n [142107.34 91391.77 366168.42 'Florida']\n [131876.9 99814.71 362861.36 'New York']\n [134615.46 147198.87 127716.82 'California']\n [130298.13 145530.06 323876.68 'Florida']\n [120542.52 148718.95 311613.29 'New York']\n [123334.88 108679.17 304981.62 'California']]\nlabelencoder:\n[[165349.2 136897.8 471784.1 2]\n [162597.7 151377.59 443898.53 0]\n [153441.51 101145.55 407934.54 1]\n [144372.41 118671.85 383199.62 2]\n [142107.34 91391.77 366168.42 1]\n [131876.9 99814.71 362861.36 2]\n [134615.46 147198.87 127716.82 0]\n [130298.13 145530.06 323876.68 1]\n [120542.52 148718.95 311613.29 2]\n [123334.88 108679.17 304981.62 0]]\nonehot:\n[[0.0 0.0 1.0 165349.2 136897.8 471784.1]\n [1.0 0.0 0.0 162597.7 151377.59 443898.53]\n [0.0 1.0 0.0 153441.51 101145.55 407934.54]\n [0.0 0.0 1.0 144372.41 118671.85 383199.62]\n [0.0 1.0 0.0 142107.34 91391.77 366168.42]\n [0.0 0.0 1.0 131876.9 99814.71 362861.36]\n [1.0 0.0 0.0 134615.46 147198.87 127716.82]\n [0.0 1.0 0.0 130298.13 145530.06 323876.68]\n [0.0 0.0 1.0 120542.52 148718.95 311613.29]\n [1.0 0.0 0.0 123334.88 108679.17 304981.62]]\n"
]
}
],
"source": [
"from sklearn.preprocessing import LabelEncoder, OneHotEncoder\n",
"from sklearn.compose import ColumnTransformer \n",
"labelencoder = LabelEncoder()\n",
"print(\"original:\")\n",
"print(X[:10])\n",
"#print(X[: , 3])\n",
"X[: , 3] = labelencoder.fit_transform(X[ : , 3])\n",
"#print(X[: , 3])\n",
"print(\"labelencoder:\")\n",
"print(X[:10])\n",
"onehotencoder = OneHotEncoder(categorical_features = [3])\n",
"X = onehotencoder.fit_transform(X).toarray()\n",
"ct = ColumnTransformer([( \"encoder\", OneHotEncoder(), [3])], remainder = 'passthrough')\n",
"X = ct.fit_transform(X)\n",
"#onehotencoder = OneHotEncoder(categorical_features = [3])\n",
"#X = onehotencoder.fit_transform(X).toarray()\n",
"print(\"onehot:\")\n",
"print(X[:10])"
]
@ -156,13 +156,31 @@
},
{
"cell_type": "code",
"execution_count": 32,
"execution_count": 61,
"metadata": {},
"outputs": [],
"source": [
"X1 = X[: , 1:]"
]
},
{
"cell_type": "code",
"execution_count": 62,
"metadata": {},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"[[0.0 1.0 165349.2 136897.8 471784.1]\n [0.0 0.0 162597.7 151377.59 443898.53]\n [1.0 0.0 153441.51 101145.55 407934.54]\n [0.0 1.0 144372.41 118671.85 383199.62]\n [1.0 0.0 142107.34 91391.77 366168.42]\n [0.0 1.0 131876.9 99814.71 362861.36]\n [0.0 0.0 134615.46 147198.87 127716.82]\n [1.0 0.0 130298.13 145530.06 323876.68]\n [0.0 1.0 120542.52 148718.95 311613.29]\n [0.0 0.0 123334.88 108679.17 304981.62]\n [1.0 0.0 101913.08 110594.11 229160.95]\n [0.0 0.0 100671.96 91790.61 249744.55]\n [1.0 0.0 93863.75 127320.38 249839.44]\n [0.0 0.0 91992.39 135495.07 252664.93]\n [1.0 0.0 119943.24 156547.42 256512.92]\n [0.0 1.0 114523.61 122616.84 261776.23]\n [0.0 0.0 78013.11 121597.55 264346.06]\n [0.0 1.0 94657.16 145077.58 282574.31]\n [1.0 0.0 91749.16 114175.79 294919.57]\n [0.0 1.0 86419.7 153514.11 224494.78489361703]\n [0.0 0.0 76253.86 113867.3 298664.47]\n [0.0 1.0 78389.47 153773.43 299737.29]\n [1.0 0.0 73994.56 122782.75 303319.26]\n [1.0 0.0 67532.53 105751.03 304768.73]\n [0.0 1.0 77044.01 99281.34 140574.81]\n [0.0 0.0 64664.71 139553.16 137962.62]\n [1.0 0.0 75328.87 144135.98 134050.07]\n [0.0 1.0 72107.6 127864.55 353183.81]\n [1.0 0.0 66051.52 182645.56 118148.2]\n [0.0 1.0 65605.48 153032.06 107138.38]\n [1.0 0.0 61994.48 115641.28 91131.24]\n [0.0 1.0 61136.38 152701.92 88218.23]\n [0.0 0.0 63408.86 129219.61 46085.25]\n [1.0 0.0 55493.95 103057.49 214634.81]\n [0.0 0.0 46426.07 157693.92 210797.67]\n [0.0 1.0 46014.02 85047.44 205517.64]\n [1.0 0.0 28663.76 127056.21 201126.82]\n [0.0 0.0 44069.95 51283.14 197029.42]\n [0.0 1.0 20229.59 65947.93 185265.1]\n [0.0 0.0 38558.51 82982.09 174999.3]\n [0.0 0.0 28754.33 118546.05 172795.67]\n [1.0 0.0 27892.92 84710.77 164470.71]\n [0.0 0.0 23640.93 96189.63 148001.11]\n [0.0 1.0 15505.73 127382.3 35534.17]\n [0.0 0.0 22177.74 154806.14 28334.72]\n [0.0 1.0 1000.23 124153.04 1903.93]\n [1.0 0.0 1315.46 115816.21 297114.46]\n [0.0 0.0 76793.34958333334 135426.92 224494.78489361703]\n [0.0 1.0 542.05 51743.15 224494.78489361703]\n [0.0 0.0 76793.34958333334 116983.8 45173.06]]\n[[0.0 0.0 1.0 165349.2 136897.8 471784.1]\n [1.0 0.0 0.0 162597.7 151377.59 443898.53]\n [0.0 1.0 0.0 153441.51 101145.55 407934.54]\n [0.0 0.0 1.0 144372.41 118671.85 383199.62]\n [0.0 1.0 0.0 142107.34 91391.77 366168.42]\n [0.0 0.0 1.0 131876.9 99814.71 362861.36]\n [1.0 0.0 0.0 134615.46 147198.87 127716.82]\n [0.0 1.0 0.0 130298.13 145530.06 323876.68]\n [0.0 0.0 1.0 120542.52 148718.95 311613.29]\n [1.0 0.0 0.0 123334.88 108679.17 304981.62]\n [0.0 1.0 0.0 101913.08 110594.11 229160.95]\n [1.0 0.0 0.0 100671.96 91790.61 249744.55]\n [0.0 1.0 0.0 93863.75 127320.38 249839.44]\n [1.0 0.0 0.0 91992.39 135495.07 252664.93]\n [0.0 1.0 0.0 119943.24 156547.42 256512.92]\n [0.0 0.0 1.0 114523.61 122616.84 261776.23]\n [1.0 0.0 0.0 78013.11 121597.55 264346.06]\n [0.0 0.0 1.0 94657.16 145077.58 282574.31]\n [0.0 1.0 0.0 91749.16 114175.79 294919.57]\n [0.0 0.0 1.0 86419.7 153514.11 224494.78489361703]\n [1.0 0.0 0.0 76253.86 113867.3 298664.47]\n [0.0 0.0 1.0 78389.47 153773.43 299737.29]\n [0.0 1.0 0.0 73994.56 122782.75 303319.26]\n [0.0 1.0 0.0 67532.53 105751.03 304768.73]\n [0.0 0.0 1.0 77044.01 99281.34 140574.81]\n [1.0 0.0 0.0 64664.71 139553.16 137962.62]\n [0.0 1.0 0.0 75328.87 144135.98 134050.07]\n [0.0 0.0 1.0 72107.6 127864.55 353183.81]\n [0.0 1.0 0.0 66051.52 182645.56 118148.2]\n [0.0 0.0 1.0 65605.48 153032.06 107138.38]\n [0.0 1.0 0.0 61994.48 115641.28 91131.24]\n [0.0 0.0 1.0 61136.38 152701.92 88218.23]\n [1.0 0.0 0.0 63408.86 129219.61 46085.25]\n [0.0 1.0 0.0 55493.95 103057.49 214634.81]\n [1.0 0.0 0.0 46426.07 157693.92 210797.67]\n [0.0 0.0 1.0 46014.02 85047.44 205517.64]\n [0.0 1.0 0.0 28663.76 127056.21 201126.82]\n [1.0 0.0 0.0 44069.95 51283.14 197029.42]\n [0.0 0.0 1.0 20229.59 65947.93 185265.1]\n [1.0 0.0 0.0 38558.51 82982.09 174999.3]\n [1.0 0.0 0.0 28754.33 118546.05 172795.67]\n [0.0 1.0 0.0 27892.92 84710.77 164470.71]\n [1.0 0.0 0.0 23640.93 96189.63 148001.11]\n [0.0 0.0 1.0 15505.73 127382.3 35534.17]\n [1.0 0.0 0.0 22177.74 154806.14 28334.72]\n [0.0 0.0 1.0 1000.23 124153.04 1903.93]\n [0.0 1.0 0.0 1315.46 115816.21 297114.46]\n [1.0 0.0 0.0 76793.34958333334 135426.92 224494.78489361703]\n [0.0 0.0 1.0 542.05 51743.15 224494.78489361703]\n [1.0 0.0 0.0 76793.34958333334 116983.8 45173.06]]\n"
]
}
],
"source": [
"print(X1)\n",
"print(X)"
]
},
{
"cell_type": "markdown",
"metadata": {},
@ -172,47 +190,14 @@
},
{
"cell_type": "code",
"execution_count": 39,
"execution_count": 63,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"name": "stdout",
"text": [
"[[0.0000000e+00 1.0000000e+00 0.0000000e+00 6.6051520e+04 1.8264556e+05\n",
" 1.1814820e+05]\n",
" [1.0000000e+00 0.0000000e+00 0.0000000e+00 1.0067196e+05 9.1790610e+04\n",
" 2.4974455e+05]\n",
" [0.0000000e+00 1.0000000e+00 0.0000000e+00 1.0191308e+05 1.1059411e+05\n",
" 2.2916095e+05]\n",
" [0.0000000e+00 1.0000000e+00 0.0000000e+00 2.7892920e+04 8.4710770e+04\n",
" 1.6447071e+05]\n",
" [0.0000000e+00 1.0000000e+00 0.0000000e+00 1.5344151e+05 1.0114555e+05\n",
" 4.0793454e+05]\n",
" [0.0000000e+00 0.0000000e+00 1.0000000e+00 7.2107600e+04 1.2786455e+05\n",
" 3.5318381e+05]\n",
" [0.0000000e+00 0.0000000e+00 1.0000000e+00 2.0229590e+04 6.5947930e+04\n",
" 1.8526510e+05]\n",
" [0.0000000e+00 0.0000000e+00 1.0000000e+00 6.1136380e+04 1.5270192e+05\n",
" 8.8218230e+04]\n",
" [0.0000000e+00 1.0000000e+00 0.0000000e+00 7.3994560e+04 1.2278275e+05\n",
" 3.0331926e+05]\n",
" [0.0000000e+00 1.0000000e+00 0.0000000e+00 1.4210734e+05 9.1391770e+04\n",
" 3.6616842e+05]]\n",
"[103282.38 144259.4 146121.95 77798.83 191050.39 105008.31 81229.06\n",
" 97483.56 110352.25 166187.94]\n",
"[[1.0000000e+00 0.0000000e+00 6.6051520e+04 1.8264556e+05 1.1814820e+05]\n",
" [0.0000000e+00 0.0000000e+00 1.0067196e+05 9.1790610e+04 2.4974455e+05]\n",
" [1.0000000e+00 0.0000000e+00 1.0191308e+05 1.1059411e+05 2.2916095e+05]\n",
" [1.0000000e+00 0.0000000e+00 2.7892920e+04 8.4710770e+04 1.6447071e+05]\n",
" [1.0000000e+00 0.0000000e+00 1.5344151e+05 1.0114555e+05 4.0793454e+05]\n",
" [0.0000000e+00 1.0000000e+00 7.2107600e+04 1.2786455e+05 3.5318381e+05]\n",
" [0.0000000e+00 1.0000000e+00 2.0229590e+04 6.5947930e+04 1.8526510e+05]\n",
" [0.0000000e+00 1.0000000e+00 6.1136380e+04 1.5270192e+05 8.8218230e+04]\n",
" [1.0000000e+00 0.0000000e+00 7.3994560e+04 1.2278275e+05 3.0331926e+05]\n",
" [1.0000000e+00 0.0000000e+00 1.4210734e+05 9.1391770e+04 3.6616842e+05]]\n",
"[103282.38 144259.4 146121.95 77798.83 191050.39 105008.31 81229.06\n",
" 97483.56 110352.25 166187.94]\n"
"[[0.0 1.0 0.0 66051.52 182645.56 118148.2]\n [1.0 0.0 0.0 100671.96 91790.61 249744.55]\n [0.0 1.0 0.0 101913.08 110594.11 229160.95]\n [0.0 1.0 0.0 27892.92 84710.77 164470.71]\n [0.0 1.0 0.0 153441.51 101145.55 407934.54]\n [0.0 0.0 1.0 72107.6 127864.55 353183.81]\n [0.0 0.0 1.0 20229.59 65947.93 185265.1]\n [0.0 0.0 1.0 61136.38 152701.92 88218.23]\n [0.0 1.0 0.0 73994.56 122782.75 303319.26]\n [0.0 1.0 0.0 142107.34 91391.77 366168.42]]\n[103282.38 144259.4 146121.95 77798.83 191050.39 105008.31 81229.06\n 97483.56 110352.25 166187.94]\n[[1.0 0.0 66051.52 182645.56 118148.2]\n [0.0 0.0 100671.96 91790.61 249744.55]\n [1.0 0.0 101913.08 110594.11 229160.95]\n [1.0 0.0 27892.92 84710.77 164470.71]\n [1.0 0.0 153441.51 101145.55 407934.54]\n [0.0 1.0 72107.6 127864.55 353183.81]\n [0.0 1.0 20229.59 65947.93 185265.1]\n [0.0 1.0 61136.38 152701.92 88218.23]\n [1.0 0.0 73994.56 122782.75 303319.26]\n [1.0 0.0 142107.34 91391.77 366168.42]]\n[103282.38 144259.4 146121.95 77798.83 191050.39 105008.31 81229.06\n 97483.56 110352.25 166187.94]\n"
]
}
],
@ -235,18 +220,18 @@
},
{
"cell_type": "code",
"execution_count": 40,
"execution_count": 64,
"metadata": {},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)"
"LinearRegression()"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
"execution_count": 64
}
],
"source": [
@ -266,7 +251,7 @@
},
{
"cell_type": "code",
"execution_count": 41,
"execution_count": 65,
"metadata": {},
"outputs": [],
"source": [
@ -276,19 +261,14 @@
},
{
"cell_type": "code",
"execution_count": 42,
"execution_count": 66,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"name": "stdout",
"text": [
"[103015.20159796 132582.27760815 132447.73845173 71976.09851258\n",
" 178537.48221051 116161.24230163 67851.69209676 98791.73374689\n",
" 113969.43533011 167921.06569547]\n",
"[103015.20159795 132582.27760817 132447.73845176 71976.09851257\n",
" 178537.48221058 116161.24230165 67851.69209675 98791.73374686\n",
" 113969.43533013 167921.06569553]\n"
"[102388.94113041 121465.72713517 127340.57708619 71709.47538912\n 174211.0848 121771.65061494 68393.54360668 95588.5313349\n 116596.3467699 162514.07218551]\n[102388.94113046 121465.72713518 127340.57708619 71709.47538916\n 174211.08479987 121771.65061482 68393.5436067 95588.53133498\n 116596.34676982 162514.07218541]\n"
]
}
],
@ -303,13 +283,6 @@
"source": [
"**完整的项目请前往Github项目100-Days-Of-ML-Code查看。有任何的建议或者意见欢迎在issue中提出~**"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
@ -328,9 +301,9 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.5"
"version": "3.8.3-final"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
}