-
Notifications
You must be signed in to change notification settings - Fork 647
/
kaggle14.py
executable file
·471 lines (460 loc) · 17.7 KB
/
kaggle14.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
import matplotlib
matplotlib.use("PS")
import modin.pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
plt.style.use("fivethirtyeight")
import warnings
warnings.filterwarnings("ignore")
data = pd.read_csv("train.csv")
data.head()
data.isnull().sum() # checking for total null values
data.groupby(["Sex", "Survived"])["Survived"].count()
f, ax = plt.subplots(1, 2, figsize=(18, 8))
data[["Sex", "Survived"]].groupby(["Sex"]).mean().plot.bar(ax=ax[0])
ax[0].set_title("Survived vs Sex")
sns.countplot("Sex", hue="Survived", data=data, ax=ax[1])
ax[1].set_title("Sex:Survived vs Dead")
plt.show()
pd.crosstab(data.Pclass, data.Survived, margins=True).style.background_gradient(
cmap="summer_r"
)
f, ax = plt.subplots(1, 2, figsize=(18, 8))
data["Pclass"].value_counts().plot.bar(
color=["#CD7F32", "#FFDF00", "#D3D3D3"], ax=ax[0]
)
ax[0].set_title("Number Of Passengers By Pclass")
ax[0].set_ylabel("Count")
sns.countplot("Pclass", hue="Survived", data=data, ax=ax[1])
ax[1].set_title("Pclass:Survived vs Dead")
plt.show()
pd.crosstab(
[data.Sex, data.Survived], data.Pclass, margins=True
).style.background_gradient(cmap="summer_r")
sns.factorplot("Pclass", "Survived", hue="Sex", data=data)
plt.show()
print("Oldest Passenger was of:", data["Age"].max(), "Years")
print("Youngest Passenger was of:", data["Age"].min(), "Years")
print("Average Age on the ship:", data["Age"].mean(), "Years")
f, ax = plt.subplots(1, 2, figsize=(18, 8))
sns.violinplot("Pclass", "Age", hue="Survived", data=data, split=True, ax=ax[0])
ax[0].set_title("Pclass and Age vs Survived")
ax[0].set_yticks(range(0, 110, 10))
sns.violinplot("Sex", "Age", hue="Survived", data=data, split=True, ax=ax[1])
ax[1].set_title("Sex and Age vs Survived")
ax[1].set_yticks(range(0, 110, 10))
plt.show()
data["Initial"] = 0
for i in data:
data["Initial"] = data.Name.str.extract(
r"([A-Za-z]+)\." # noqa: W605
) # lets extract the Salutations
pd.crosstab(data.Initial, data.Sex).T.style.background_gradient(
cmap="summer_r"
) # Checking the Initials with the Sex
data["Initial"].replace(
[
"Mlle",
"Mme",
"Ms",
"Dr",
"Major",
"Lady",
"Countess",
"Jonkheer",
"Col",
"Rev",
"Capt",
"Sir",
"Don",
],
[
"Miss",
"Miss",
"Miss",
"Mr",
"Mr",
"Mrs",
"Mrs",
"Other",
"Other",
"Other",
"Mr",
"Mr",
"Mr",
],
inplace=True,
)
data.groupby("Initial")["Age"].mean() # lets check the average age by Initials
data.loc[(data.Age.isnull()) & (data.Initial == "Mr"), "Age"] = 33
data.loc[(data.Age.isnull()) & (data.Initial == "Mrs"), "Age"] = 36
data.loc[(data.Age.isnull()) & (data.Initial == "Master"), "Age"] = 5
data.loc[(data.Age.isnull()) & (data.Initial == "Miss"), "Age"] = 22
data.loc[(data.Age.isnull()) & (data.Initial == "Other"), "Age"] = 46
data.Age.isnull().any() # So no null values left finally
f, ax = plt.subplots(1, 2, figsize=(20, 10))
data[data["Survived"] == 0].Age.plot.hist(
ax=ax[0], bins=20, edgecolor="black", color="red"
)
ax[0].set_title("Survived= 0")
x1 = list(range(0, 85, 5))
ax[0].set_xticks(x1)
data[data["Survived"] == 1].Age.plot.hist(
ax=ax[1], color="green", bins=20, edgecolor="black"
)
ax[1].set_title("Survived= 1")
x2 = list(range(0, 85, 5))
ax[1].set_xticks(x2)
plt.show()
sns.factorplot("Pclass", "Survived", col="Initial", data=data)
plt.show()
pd.crosstab(
[data.Embarked, data.Pclass], [data.Sex, data.Survived], margins=True
).style.background_gradient(cmap="summer_r")
sns.factorplot("Embarked", "Survived", data=data)
fig = plt.gcf()
fig.set_size_inches(5, 3)
plt.show()
f, ax = plt.subplots(2, 2, figsize=(20, 15))
sns.countplot("Embarked", data=data, ax=ax[0, 0])
ax[0, 0].set_title("No. Of Passengers Boarded")
sns.countplot("Embarked", hue="Sex", data=data, ax=ax[0, 1])
ax[0, 1].set_title("Male-Female Split for Embarked")
sns.countplot("Embarked", hue="Survived", data=data, ax=ax[1, 0])
ax[1, 0].set_title("Embarked vs Survived")
sns.countplot("Embarked", hue="Pclass", data=data, ax=ax[1, 1])
ax[1, 1].set_title("Embarked vs Pclass")
plt.subplots_adjust(wspace=0.2, hspace=0.5)
plt.show()
sns.factorplot("Pclass", "Survived", hue="Sex", col="Embarked", data=data)
plt.show()
data["Embarked"].fillna("S", inplace=True)
data.Embarked.isnull().any() # Finally No NaN values
pd.crosstab([data.SibSp], data.Survived).style.background_gradient(cmap="summer_r")
f, ax = plt.subplots(1, 2, figsize=(20, 8))
sns.barplot("SibSp", "Survived", data=data, ax=ax[0])
ax[0].set_title("SibSp vs Survived")
sns.factorplot("SibSp", "Survived", data=data, ax=ax[1])
ax[1].set_title("SibSp vs Survived")
plt.close(2)
plt.show()
pd.crosstab(data.SibSp, data.Pclass).style.background_gradient(cmap="summer_r")
pd.crosstab(data.Parch, data.Pclass).style.background_gradient(cmap="summer_r")
f, ax = plt.subplots(1, 2, figsize=(20, 8))
sns.barplot("Parch", "Survived", data=data, ax=ax[0])
ax[0].set_title("Parch vs Survived")
sns.factorplot("Parch", "Survived", data=data, ax=ax[1])
ax[1].set_title("Parch vs Survived")
plt.close(2)
plt.show()
print("Highest Fare was:", data["Fare"].max())
print("Lowest Fare was:", data["Fare"].min())
print("Average Fare was:", data["Fare"].mean())
f, ax = plt.subplots(1, 3, figsize=(20, 8))
sns.distplot(data[data["Pclass"] == 1].Fare, ax=ax[0])
ax[0].set_title("Fares in Pclass 1")
sns.distplot(data[data["Pclass"] == 2].Fare, ax=ax[1])
ax[1].set_title("Fares in Pclass 2")
sns.distplot(data[data["Pclass"] == 3].Fare, ax=ax[2])
ax[2].set_title("Fares in Pclass 3")
plt.show()
sns.heatmap(
data.corr(), annot=True, cmap="RdYlGn", linewidths=0.2
) # data.corr()-->correlation matrix
fig = plt.gcf()
fig.set_size_inches(10, 8)
plt.show()
data["Age_band"] = 0
data.loc[data["Age"] <= 16, "Age_band"] = 0
data.loc[(data["Age"] > 16) & (data["Age"] <= 32), "Age_band"] = 1
data.loc[(data["Age"] > 32) & (data["Age"] <= 48), "Age_band"] = 2
data.loc[(data["Age"] > 48) & (data["Age"] <= 64), "Age_band"] = 3
data.loc[data["Age"] > 64, "Age_band"] = 4
data.head(2)
data["Age_band"].value_counts().to_frame().style.background_gradient(
cmap="summer"
) # checking the number of passenegers in each band
sns.factorplot("Age_band", "Survived", data=data, col="Pclass")
plt.show()
data["Family_Size"] = 0
data["Family_Size"] = data["Parch"] + data["SibSp"] # family size
data["Alone"] = 0
data.loc[data.Family_Size == 0, "Alone"] = 1 # Alone
f, ax = plt.subplots(1, 2, figsize=(18, 6))
sns.factorplot("Family_Size", "Survived", data=data, ax=ax[0])
ax[0].set_title("Family_Size vs Survived")
sns.factorplot("Alone", "Survived", data=data, ax=ax[1])
ax[1].set_title("Alone vs Survived")
plt.close(2)
plt.close(3)
plt.show()
sns.factorplot("Alone", "Survived", data=data, hue="Sex", col="Pclass")
plt.show()
data["Fare_Range"] = pd.qcut(data["Fare"], 4)
data.groupby(["Fare_Range"])["Survived"].mean().to_frame().style.background_gradient(
cmap="summer_r"
)
data["Fare_cat"] = 0
data.loc[data["Fare"] <= 7.91, "Fare_cat"] = 0
data.loc[(data["Fare"] > 7.91) & (data["Fare"] <= 14.454), "Fare_cat"] = 1
data.loc[(data["Fare"] > 14.454) & (data["Fare"] <= 31), "Fare_cat"] = 2
data.loc[(data["Fare"] > 31) & (data["Fare"] <= 513), "Fare_cat"] = 3
sns.factorplot("Fare_cat", "Survived", data=data, hue="Sex")
plt.show()
data["Sex"].replace(["male", "female"], [0, 1], inplace=True)
data["Embarked"].replace(["S", "C", "Q"], [0, 1, 2], inplace=True)
data["Initial"].replace(
["Mr", "Mrs", "Miss", "Master", "Other"], [0, 1, 2, 3, 4], inplace=True
)
data.drop(
["Name", "Age", "Ticket", "Fare", "Cabin", "Fare_Range", "PassengerId"],
axis=1,
inplace=True,
)
sns.heatmap(
data.corr(), annot=True, cmap="RdYlGn", linewidths=0.2, annot_kws={"size": 20}
)
fig = plt.gcf()
fig.set_size_inches(18, 15)
plt.xticks(fontsize=14)
plt.yticks(fontsize=14)
plt.show()
from sklearn.linear_model import LogisticRegression # logistic regression
from sklearn import svm # support vector Machine
from sklearn.ensemble import RandomForestClassifier # Random Forest
from sklearn.neighbors import KNeighborsClassifier # KNN
from sklearn.naive_bayes import GaussianNB # Naive bayes
from sklearn.tree import DecisionTreeClassifier # Decision Tree
from sklearn.model_selection import train_test_split # training and testing data split
from sklearn import metrics # accuracy measure
from sklearn.metrics import confusion_matrix # for confusion matrix
train, test = train_test_split(
data, test_size=0.3, random_state=0, stratify=data["Survived"]
)
train_X = train[train.columns[1:]]
train_Y = train[train.columns[:1]]
test_X = test[test.columns[1:]]
test_Y = test[test.columns[:1]]
X = data[data.columns[1:]]
Y = data["Survived"]
model = svm.SVC(kernel="rbf", C=1, gamma=0.1)
model.fit(train_X, train_Y)
prediction1 = model.predict(test_X)
print("Accuracy for rbf SVM is ", metrics.accuracy_score(prediction1, test_Y))
model = svm.SVC(kernel="linear", C=0.1, gamma=0.1)
model.fit(train_X, train_Y)
prediction2 = model.predict(test_X)
print("Accuracy for linear SVM is", metrics.accuracy_score(prediction2, test_Y))
model = LogisticRegression()
model.fit(train_X, train_Y)
prediction3 = model.predict(test_X)
print(
"The accuracy of the Logistic Regression is",
metrics.accuracy_score(prediction3, test_Y),
)
model = DecisionTreeClassifier()
model.fit(train_X, train_Y)
prediction4 = model.predict(test_X)
print(
"The accuracy of the Decision Tree is", metrics.accuracy_score(prediction4, test_Y)
)
model = KNeighborsClassifier()
model.fit(train_X, train_Y)
prediction5 = model.predict(test_X)
print("The accuracy of the KNN is", metrics.accuracy_score(prediction5, test_Y))
a_index = list(range(1, 11))
a = pd.Series()
x = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
for i in list(range(1, 11)):
model = KNeighborsClassifier(n_neighbors=i)
model.fit(train_X, train_Y)
prediction = model.predict(test_X)
a = a.append(pd.Series(metrics.accuracy_score(prediction, test_Y)))
plt.plot(a_index, a)
plt.xticks(x)
fig = plt.gcf()
fig.set_size_inches(12, 6)
plt.show()
print(
"Accuracies for different values of n are:",
a.values,
"with the max value as ",
a.values.max(),
)
model = GaussianNB()
model.fit(train_X, train_Y)
prediction6 = model.predict(test_X)
print("The accuracy of the NaiveBayes is", metrics.accuracy_score(prediction6, test_Y))
model = RandomForestClassifier(n_estimators=100)
model.fit(train_X, train_Y)
prediction7 = model.predict(test_X)
print(
"The accuracy of the Random Forests is", metrics.accuracy_score(prediction7, test_Y)
)
from sklearn.model_selection import KFold # for K-fold cross validation
from sklearn.model_selection import cross_val_score # score evaluation
from sklearn.model_selection import cross_val_predict # prediction
kfold = KFold(n_splits=10, random_state=22) # k=10, split the data into 10 equal parts
xyz = []
accuracy = []
std = []
classifiers = [
"Linear Svm",
"Radial Svm",
"Logistic Regression",
"KNN",
"Decision Tree",
"Naive Bayes",
"Random Forest",
]
models = [
svm.SVC(kernel="linear"),
svm.SVC(kernel="rbf"),
LogisticRegression(),
KNeighborsClassifier(n_neighbors=9),
DecisionTreeClassifier(),
GaussianNB(),
RandomForestClassifier(n_estimators=100),
]
for i in models:
model = i
cv_result = cross_val_score(model, X, Y, cv=kfold, scoring="accuracy")
xyz.append(cv_result.mean())
std.append(cv_result.std())
accuracy.append(cv_result)
new_models_dataframe2 = pd.DataFrame({"CV Mean": xyz, "Std": std}, index=classifiers)
new_models_dataframe2
plt.subplots(figsize=(12, 6))
box = pd.DataFrame(accuracy, index=[classifiers])
box.T.boxplot()
new_models_dataframe2["CV Mean"].plot.barh(width=0.8)
plt.title("Average CV Mean Accuracy")
fig = plt.gcf()
fig.set_size_inches(8, 5)
plt.show()
f, ax = plt.subplots(3, 3, figsize=(12, 10))
y_pred = cross_val_predict(svm.SVC(kernel="rbf"), X, Y, cv=10)
sns.heatmap(confusion_matrix(Y, y_pred), ax=ax[0, 0], annot=True, fmt="2.0f")
ax[0, 0].set_title("Matrix for rbf-SVM")
y_pred = cross_val_predict(svm.SVC(kernel="linear"), X, Y, cv=10)
sns.heatmap(confusion_matrix(Y, y_pred), ax=ax[0, 1], annot=True, fmt="2.0f")
ax[0, 1].set_title("Matrix for Linear-SVM")
y_pred = cross_val_predict(KNeighborsClassifier(n_neighbors=9), X, Y, cv=10)
sns.heatmap(confusion_matrix(Y, y_pred), ax=ax[0, 2], annot=True, fmt="2.0f")
ax[0, 2].set_title("Matrix for KNN")
y_pred = cross_val_predict(RandomForestClassifier(n_estimators=100), X, Y, cv=10)
sns.heatmap(confusion_matrix(Y, y_pred), ax=ax[1, 0], annot=True, fmt="2.0f")
ax[1, 0].set_title("Matrix for Random-Forests")
y_pred = cross_val_predict(LogisticRegression(), X, Y, cv=10)
sns.heatmap(confusion_matrix(Y, y_pred), ax=ax[1, 1], annot=True, fmt="2.0f")
ax[1, 1].set_title("Matrix for Logistic Regression")
y_pred = cross_val_predict(DecisionTreeClassifier(), X, Y, cv=10)
sns.heatmap(confusion_matrix(Y, y_pred), ax=ax[1, 2], annot=True, fmt="2.0f")
ax[1, 2].set_title("Matrix for Decision Tree")
y_pred = cross_val_predict(GaussianNB(), X, Y, cv=10)
sns.heatmap(confusion_matrix(Y, y_pred), ax=ax[2, 0], annot=True, fmt="2.0f")
ax[2, 0].set_title("Matrix for Naive Bayes")
plt.subplots_adjust(hspace=0.2, wspace=0.2)
plt.show()
from sklearn.model_selection import GridSearchCV
C = [0.05, 0.1, 0.2, 0.3, 0.25, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1]
gamma = [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0]
kernel = ["rbf", "linear"]
hyper = {"kernel": kernel, "C": C, "gamma": gamma}
gd = GridSearchCV(estimator=svm.SVC(), param_grid=hyper, verbose=True)
gd.fit(X, Y)
print(gd.best_score_)
print(gd.best_estimator_)
n_estimators = range(100, 1000, 100)
hyper = {"n_estimators": n_estimators}
gd = GridSearchCV(
estimator=RandomForestClassifier(random_state=0), param_grid=hyper, verbose=True
)
gd.fit(X, Y)
print(gd.best_score_)
print(gd.best_estimator_)
from sklearn.ensemble import VotingClassifier
ensemble_lin_rbf = VotingClassifier(
estimators=[
("KNN", KNeighborsClassifier(n_neighbors=10)),
("RBF", svm.SVC(probability=True, kernel="rbf", C=0.5, gamma=0.1)),
("RFor", RandomForestClassifier(n_estimators=500, random_state=0)),
("LR", LogisticRegression(C=0.05)),
("DT", DecisionTreeClassifier(random_state=0)),
("NB", GaussianNB()),
("svm", svm.SVC(kernel="linear", probability=True)),
],
voting="soft",
).fit(train_X, train_Y)
print("The accuracy for ensembled model is:", ensemble_lin_rbf.score(test_X, test_Y))
cross = cross_val_score(ensemble_lin_rbf, X, Y, cv=10, scoring="accuracy")
print("The cross validated score is", cross.mean())
from sklearn.ensemble import BaggingClassifier
model = BaggingClassifier(
base_estimator=KNeighborsClassifier(n_neighbors=3), random_state=0, n_estimators=700
)
model.fit(train_X, train_Y)
prediction = model.predict(test_X)
print("The accuracy for bagged KNN is:", metrics.accuracy_score(prediction, test_Y))
result = cross_val_score(model, X, Y, cv=10, scoring="accuracy")
print("The cross validated score for bagged KNN is:", result.mean())
model = BaggingClassifier(
base_estimator=DecisionTreeClassifier(), random_state=0, n_estimators=100
)
model.fit(train_X, train_Y)
prediction = model.predict(test_X)
print(
"The accuracy for bagged Decision Tree is:",
metrics.accuracy_score(prediction, test_Y),
)
result = cross_val_score(model, X, Y, cv=10, scoring="accuracy")
print("The cross validated score for bagged Decision Tree is:", result.mean())
from sklearn.ensemble import AdaBoostClassifier
ada = AdaBoostClassifier(n_estimators=200, random_state=0, learning_rate=0.1)
result = cross_val_score(ada, X, Y, cv=10, scoring="accuracy")
print("The cross validated score for AdaBoost is:", result.mean())
from sklearn.ensemble import GradientBoostingClassifier
grad = GradientBoostingClassifier(n_estimators=500, random_state=0, learning_rate=0.1)
result = cross_val_score(grad, X, Y, cv=10, scoring="accuracy")
print("The cross validated score for Gradient Boosting is:", result.mean())
import xgboost as xg
xgboost = xg.XGBClassifier(n_estimators=900, learning_rate=0.1)
result = cross_val_score(xgboost, X, Y, cv=10, scoring="accuracy")
print("The cross validated score for XGBoost is:", result.mean())
n_estimators = list(range(100, 1100, 100))
learn_rate = [0.05, 0.1, 0.2, 0.3, 0.25, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1]
hyper = {"n_estimators": n_estimators, "learning_rate": learn_rate}
gd = GridSearchCV(estimator=AdaBoostClassifier(), param_grid=hyper, verbose=True)
gd.fit(X, Y)
print(gd.best_score_)
print(gd.best_estimator_)
ada = AdaBoostClassifier(n_estimators=200, random_state=0, learning_rate=0.05)
result = cross_val_predict(ada, X, Y, cv=10)
sns.heatmap(confusion_matrix(Y, result), cmap="winter", annot=True, fmt="2.0f")
plt.show()
f, ax = plt.subplots(2, 2, figsize=(15, 12))
model = RandomForestClassifier(n_estimators=500, random_state=0)
model.fit(X, Y)
pd.Series(model.feature_importances_, X.columns).sort_values(ascending=True).plot.barh(
width=0.8, ax=ax[0, 0]
)
ax[0, 0].set_title("Feature Importance in Random Forests")
model = AdaBoostClassifier(n_estimators=200, learning_rate=0.05, random_state=0)
model.fit(X, Y)
pd.Series(model.feature_importances_, X.columns).sort_values(ascending=True).plot.barh(
width=0.8, ax=ax[0, 1], color="#ddff11"
)
ax[0, 1].set_title("Feature Importance in AdaBoost")
model = GradientBoostingClassifier(n_estimators=500, learning_rate=0.1, random_state=0)
model.fit(X, Y)
pd.Series(model.feature_importances_, X.columns).sort_values(ascending=True).plot.barh(
width=0.8, ax=ax[1, 0], cmap="RdYlGn_r"
)
ax[1, 0].set_title("Feature Importance in Gradient Boosting")
model = xg.XGBClassifier(n_estimators=900, learning_rate=0.1)
model.fit(X, Y)
pd.Series(model.feature_importances_, X.columns).sort_values(ascending=True).plot.barh(
width=0.8, ax=ax[1, 1], color="#FD0F00"
)
ax[1, 1].set_title("Feature Importance in XgBoost")
plt.show()