def prepare_data():
ansur_ii_male = load_ansur_ii_male_data().sample(500)
ansur_ii_female = load_ansur_ii_female_data().sample(500)
df = pd.concat([ansur_ii_male, ansur_ii_female])
non_numeric = [
'Branch', 'Gender', 'Component', "weight_kg", "stature_m", "BMI_class",
"Height_class"
]
ansur_df = df.drop(non_numeric, axis=1)
return ansur_df
def prepare_data():
ansur_ii_male = load_ansur_ii_male_data().sample(500)
ansur_ii_female = load_ansur_ii_female_data().sample(500)
df = pd.concat([ansur_ii_male, ansur_ii_female])
cols = [
'elbowrestheight', 'wristcircumference', 'anklecircumference',
'buttockheight', 'crotchheight'
]
ansur_df = df[cols]
return ansur_df
def prepare_data():
ansur_ii_male = load_ansur_ii_male_data().sample(500)
ansur_ii_female = load_ansur_ii_female_data().sample(500)
df = pd.concat([ansur_ii_male, ansur_ii_female])
cols = [
'headbreadth', 'headcircumference', 'headlength', 'tragiontopofhead'
]
head_df = df[cols]
head_df["n_hairs"] = np.random.normal(100000, 10)
head_df["measurement_error"] = np.random.normal(0.1, 1.387893e-17)
return head_df
def prepare_data():
ansur_ii_male = load_ansur_ii_male_data()
cols = [
'stature_m', 'buttockheight', 'waistcircumference',
'shouldercircumference'
]
ansur_df = ansur_ii_male[cols].sample(250)
# X = ansur_ii_male[cols]
# y = ansur_ii_male["bicepscircumferenceflexed"]
# X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
# return X_train, X_test, y_train, y_test, X, y
return ansur_df
def prepare_data():
ansur_ii_male = load_ansur_ii_male_data().sample(1000)
cols = [
'acromialheight', 'axillaheight', 'bideltoidbreadth',
'buttockcircumference', 'buttockkneelength', 'buttockpopliteallength',
'cervicaleheight', 'chestcircumference', 'chestheight',
'earprotrusion', 'footbreadthhorizontal', 'forearmcircumferenceflexed',
'handlength', 'headbreadth', 'heelbreadth', 'hipbreadth',
'iliocristaleheight', 'interscyeii', 'lateralfemoralepicondyleheight',
'lateralmalleolusheight', 'neckcircumferencebase',
'radialestylionlength', 'shouldercircumference', 'shoulderelbowlength',
'sleeveoutseam', 'thighcircumference', 'thighclearance',
'verticaltrunkcircumferenceusa', 'waistcircumference', 'waistdepth',
'wristheight', 'BMI'
]
X = ansur_ii_male[cols]
y = ansur_ii_male["bicepscircumferenceflexed"]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
return X_train, X_test, y_train, y_test, X, y
def pca_on_larger_dataset():
ansur_ii_male = load_ansur_ii_male_data()
cols = [
'stature_m', 'buttockheight', 'waistdepth', 'span',
'waistcircumference', 'shouldercircumference', 'footlength',
'handlength', 'functionalleglength', 'chestheight',
'chestcircumference', 'cervicaleheight', 'sittingheight'
]
ansur_df = ansur_ii_male[cols].sample(250)
# Scale the data
scaler = StandardScaler()
ansur_std = scaler.fit_transform(ansur_df)
# Apply PCA
pca = PCA()
pca.fit(ansur_std)
# Inspect the explained variance ratio per component
print(pca.explained_variance_ratio_)
# Print the cumulative sum of the explained variance ratio
print(pca.explained_variance_ratio_.cumsum())
# Fit and transform the t-SNE model on the numeric dataset
tsne_features = m.fit_transform(df_numeric)
print(tsne_features.shape)
return tsne_features
def tsne_visualization_of_dimensionality(df, tsne_features):
df["x"] = tsne_features[:, 0]
df["y"] = tsne_features[:, 1]
# Color the points according to Army Component
sns.scatterplot(x="x", y="y", hue="Component", data=df)
# Show the plot
plt.show()
# Color the points by Army Branch
sns.scatterplot(x="x", y="y", hue="Branch", data=df)
plt.show()
# Color the points by Gender
sns.scatterplot(x="x", y="y", hue="Gender", data=df)
plt.show()
ansur_ii_male = load_ansur_ii_male_data()
ansur_ii_female = load_ansur_ii_female_data()
df = pd.concat([ansur_ii_male, ansur_ii_female])
tsne_features = fitting_tsne_to_ansur_data(df)
tsne_visualization_of_dimensionality(df, tsne_features)
def accuracy_after_dimensionality_reduction(ansur_df):
# Assign just the 'neckcircumferencebase' column from ansur_df to X
X = ansur_df[["neckcircumferencebase"]]
y = ansur_df["Gender"]
# Split the data, instantiate a classifier and fit the data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
svc = SVC()
svc.fit(X_train, y_train)
# Calculate accuracy scores on both train and test data
accuracy_train = accuracy_score(y_train, svc.predict(X_train))
accuracy_test = accuracy_score(y_test, svc.predict(X_test))
print("{0:.1%} accuracy on test set vs. {1:.1%} on training set".format(
accuracy_test, accuracy_train))
ansur_ii_male = load_ansur_ii_male_data().sample(500)
ansur_ii_female = load_ansur_ii_female_data().sample(500)
df = pd.concat([ansur_ii_male, ansur_ii_female])
non_numeric = [
'Branch', 'Component', "weight_kg", "stature_m", "BMI", "BMI_class",
"Height_class"
]
df.drop(non_numeric, axis=1, inplace=True)
accuracy_with_large_dimension(df)
accuracy_after_dimensionality_reduction(df)
def prepare_data():
ansur_ii_male = load_ansur_ii_male_data().sample(500)
ansur_ii_female = load_ansur_ii_female_data().sample(500)
df = pd.concat([ansur_ii_male, ansur_ii_female])
return df